Skip to content
Apothem
Perintah pipeline

Perintah pipeline

Referensi perintah pipeline Apothem — alur /plan dan katalog perintah audit.

Apothem mengirimkan pipeline /plan yang sadar arsitektur, pipeline /research tiga belas tahap, ditambah urutan audit sebelas perintah — memberikan setiap proyek jalur terstruktur dari prosa mentah menuju kode berkelas produksi yang ditinjau dari banyak sumbu, dan dari ide mentah menuju makalah yang telah ditelaah sejawat dan disebarluaskan.

Gambaran umum pipeline

flowchart LR
    accTitle: Plan pipeline command flow
    accDescr: Left-to-right flowchart of the apothem plan pipeline from the spec stage through the generate and review stages, then through a conditional architecture-bearing decision that either runs the design stage or skips directly to the execute stage. The orthogonal audit stage wraps the spec-through-review span as a closed remediation loop, and the re-entrant amend stage revises an existing suite and returns it to review.
    A[/plan-spec] --> B[/plan-generate]
    B --> C[/plan-review]
    AUD[/plan-audit<br/>orthogonal: wraps spec → review] -.->|closed-loop remediation| A
    AM[/plan-amend<br/>re-entrant: revises an existing suite] -.->|re-review| C
    C --> Q{Architecture-bearing suite?}
    Q -->|yes| F[/plan-design<br/>emit _inputs/design.md]
    Q -->|no| D[/plan-execute]
    F --> D
    D --> E[/plan-status]
    D --> G[Audit review sequence]
    G --> H[Completion milestone]

Tahap-tahap perencanaan

Pipeline ini dikirimkan sebagai delapan perintah garis miring kelas satu, satu per tahap — masing-masing dapat dipanggil secara independen sebagai /plan-<stage>. Orkestrator /plan menggerakkan tahap-tahap tersebut dari sebuah misi hingga suite yang telah dieksekusi.

TahapPeranPosisi
/plan-specPenempa — dari prosa ke spesifikasiAwal
/plan-generateGenerator — dari spesifikasi ke suite rencanaTengah rantai
/plan-reviewAuditor — audit rencana forensikTengah rantai
/plan-designArsitek — _inputs/design.md untuk suite yang menyangkut arsitekturGerbang bersyarat
/plan-executeEksekutor — eksekusi faseTerminal
/plan-statusPelapor — status hanya-bacaHanya-baca
/plan-auditPenjaga — pembungkus lingkar tertutup atas spec → generate → reviewOrtogonal (pra-eksekusi)
/plan-amendPengurus — amandemen re-entran atas suite yang sudah adaRe-entran

/plan-audit bersifat ortogonal terhadap alur linear, bukan tahap di dalamnya. Perintah ini membungkus /plan-spec → /plan-generate → /plan-review sebagai satu lingkar tertutup, hanya menjalankan tahap hulu yang belum ada, secara aktif meremediasi temuan, dan meninggalkan suite dalam keadaan siap untuk /plan-execute. Perintah ini berbeda dari urutan tinjauan audit di bawah, yang mengaudit basis kode yang telah dieksekusi alih-alih suite rencana.

/plan-design bukan seremoni universal. /plan-review mengklasifikasikan apakah suite mengubah permukaan yang menyangkut arsitektur. Jika ya, /plan-design memancarkan jejak desain yang dikonsumsi /plan-execute dan /architecture-review. Jika tidak, suite yang telah ditinjau langsung masuk ke eksekusi.

Pipeline riset

Pipeline riset dikirimkan sebagai tiga belas perintah garis miring kelas satu, satu per tahap — masing-masing dapat dipanggil secara independen sebagai /research-<stage>, dirangkai oleh Sequence Gate dan Handoff Manifest, di bawah sepuluh mandat ketelitian (sumber otoritatif, reprodusibilitas, falsifiabilitas, integritas sitasi, praregistrasi, etika / konflik kepentingan, ketelitian statistik, sains terbuka / FAIR, kepatuhan pada pedoman pelaporan, landasan teoretis / dampak).

flowchart LR
    accTitle: Research pipeline command flow
    accDescr: Left-to-right flowchart of the apothem research pipeline from the ideate stage through spec, theory, sources, synthesis, proposal, study design, experiment, analysis, paper, and peer review to publish and disseminate, with a revision loop from review back to paper.
    RI[/research-ideate] --> RS[/research-spec]
    RS --> RT[/research-theory]
    RT --> RSO[/research-sources]
    RSO --> RSY[/research-synthesis]
    RSY --> RPR[/research-proposal]
    RPR --> RD[/research-design]
    RD --> RE[/research-experiment]
    RE --> RA[/research-analysis]
    RA --> RP[/research-paper]
    RP --> RR[/research-review]
    RR --> RPU[/research-publish]
    RPU --> RDI[/research-disseminate]
    RR -.->|revision loop| RP
TahapPeranPosisi
/research-ideateMerumuskan masalah — pertanyaan kandidat dari benih domainAwal
/research-specMembingkai pertanyaan — hipotesis yang dapat difalsifikasi + cakupanTengah rantai
/research-theoryKerangka konseptual + teori perubahanTengah rantai
/research-sourcesPengumpulan sumber secara sistematis dengan catatan pencarian yang dapat dijalankan ulangTengah rantai
/research-synthesisPeta SOTA + analisis celahTengah rantai
/research-proposalTujuan + kelayakan + kontingensi + dampak + rencana data + rencana praregistrasi; matriks panggilan pendanaan atau tanggapan pengajuan ulangTengah rantai
/research-designDesain studi + praregistrasiTengah rantai
/research-experimentMenjalankan + mencatat, dapat direproduksiTengah rantai
/research-analysisHasil + statistikTengah rantai
/research-paperDraf makalah kelas atasTengah rantai
/research-reviewKritik setara telaah sejawatTengah rantai
/research-publishPaket venue + pengajuanTengah rantai
/research-disseminateDiseminasi + dampak + pengarsipan FAIRTerminal

Orkestrator alur kerja terbungkus /research menggerakkan tahap-tahap ini dari pertanyaan mentah hingga makalah yang terbit (orkestrator itu sendiri bukan sebuah tahap), dengan memeriksa keluaran setiap tahap secara independen sebelum tahap berikutnya dibangun di atasnya; --quick hanya menjalankan /research-sources + /research-synthesis untuk laporan bersitasi sekali jalan.

Tahap-tahap empiris (sumber, desain, eksperimen, analisis) dan tahap-tahap penulisan (makalah, tinjauan, publikasi, diseminasi) juga memanfaatkan permukaan yang mengoperasionalkan ketelitian — perbandingan multi-metode yang adil, provenance pembanding, kerangka program eksperimen, rencana pemanfaatan komputasi, lingkar eksperimen otonom yang opt-in, gerbang kemajuan definition-of-done, pembutaan dengan pengungkapan bertahap, catatan pencarian, perencanaan alokasi studi dan daya, disiplin analisis, kontingensi rencana, integritas gambar, serta perencanaan presentasi dan poster — yang menambahkan detail operasional pada kesepuluh mandat tanpa memperluasnya.

Urutan tinjauan audit

Orkestrator alur kerja terbungkus /audit menyapu kesebelas dimensi di bawah ini dalam satu lintasan paralel — padanan audit-fortress dari /plan dan /research — dan menyintesis satu laporan temuan yang telah dideduplikasi dan ditriase menurut tingkat keparahan (hanya laporan; remediasi diarahkan ke /elevate). Setiap dimensi juga dapat dipanggil secara terpisah.

Orkestrator alur kerja terbungkus /fortress menutup lingkar yang dilaporkan /audit: orkestrator ini mendeteksi melalui /audit, memverifikasi setiap temuan, meremediasi setiap temuan yang bertahan pada permukaan pemiliknya, mengaudit ulang dalam lingkar yang dibatasi, dan menggerbangkan hasilnya melalui /release-readiness — padanan pengerasan produksi dari /plan dan /research.

PerintahArea kualitas
/code-reviewKualitas kode
/code-auditKorpus kode
/security-auditOWASP / ASVS
/perf-auditKinerja
/architecture-reviewArsitektur
/ux-reviewPengalaman pengembang
/a11y-auditAksesibilitas
/docs-reviewDokumentasi
/dependency-auditDependensi
/supply-chain-auditRantai pasok
/threat-model-auditModel ancaman

Semua perintah

Setiap perintah yang dikirimkan, dihasilkan dari definisinya di bawah src/apothem/commands/. Perintah tanpa halaman yang ditulis tangan mendapatkan halaman yang dihasilkan dari definisi yang sama.

CommandSummary
/planRuns the planning pipeline (spec, generate, review, design) with independent verification, confirming at each hand-off; execute stays a manual step the …
/plan-specTurns free-form prose, notes or rough requirements into a spec-grade _spec/spec.md that keeps the author's wording and settles open questions by inquiry.
/plan-generateGenerates a full plan suite (master plan, progress log, decision notes, per-phase files) from a written spec or raw prose.
/plan-reviewReads an existing plan suite line by line for fidelity, consistency, completeness and risk, then applies only the revisions the user approves.
/plan-designWrites the architectural design for a reviewed plan suite at _inputs/design.md: components, interfaces, decisions and diagrams.
/plan-executeUse to implement one phase of a reviewed plan suite: reads the phase file and progress notes, verifies prerequisites and review scorecards, implements each …
/plan-amendChanges an existing plan suite without losing resolved decisions, re-deriving only the affected spec, phases and notes.
/plan-auditAudits a plan suite across spec, generate and review, then fixes findings in a loop without per-revision approval until none remain or the cap is hit.
/plan-statusReports plan-suite progress from its tracking files across tasks, phases and artifacts, read-only.
/researchRuns the research pipeline from idea to peer-reviewed paper, verifying each stage hand-off and halting before data collection or publication.
/research-ideateFinds a research question from zero by scanning opportunities, gaps, and invalidated hypotheses, then ranking candidates.
/research-specFrames a research question or notes into a testable spec: falsifiable hypotheses, inclusion and exclusion scope, success metrics.
/research-theoryBuilds the conceptual framework for a framed research question: theory of change, constructs with operational definitions and a conceptual-model diagram.
/research-sourcesCollects and screens the literature for a ratified research spec: deduplication, ranking and extraction with provenance.
/research-synthesisReconciles collected sources into a state-of-the-art map, a literature matrix and a research-gap statement.
/research-proposalTurns a research gap and theoretical framework into a fundable proposal: SMART aims, feasibility, risk register with contingencies, impact pathway, data …
/research-designTurns a synthesized research gap into testable predictions, a study design and a frozen preregistration.
/research-experimentRuns the preregistered study protocol and records raw data with provenance: experiment log, data, and reproducibility manifest (environment, seed, version …
/research-analysisRuns the preregistered statistical analysis on collected data: effect sizes with confidence intervals, multiple-comparison correction, robustness checks, …
/research-paperAssembles a paper draft from the synthesis, study design, and analysis, with every citation checked to resolve.
/research-reviewHostile peer review of a paper, from a research suite or a supplied PDF or text: scores novelty, rigor, reproducibility, ethics; ranks revisions.
/research-publishBuilds the venue submission package for a reviewed paper: template formatting, cover letter, data and code availability statement, ethics and conflict …
/research-disseminatePlans post-acceptance dissemination and impact: preprint announcement, FAIR data and code archive, altmetrics tracking, rebuttal loop.
/auditSweeps a repository across all eleven review dimensions in one multi-agent run and returns one verified, severity-ranked report; it never fixes anything.
/a11y-auditAudits rendered pages of a web surface against WCAG 2.2 AA and reports severity-ranked findings per page, without fixing anything.
/architecture-reviewReviews a repository against its design document and layer rules, reporting boundary violations, coupling and wiring gaps as ranked findings.
/code-auditCross-file forensic audit: hidden coupling, type-hint gaps, coverage holes, dead and duplicate code.
/code-reviewReviews source files one at a time for readability, naming, complexity, idiom fit and comment quality, and reports severity-ranked findings without editing.
/dependency-auditAudits direct and transitive dependencies for known vulnerabilities, license conflicts, deprecation and loose pins, ranking findings per dependency.
/docs-reviewReviews documentation pages for prose clarity, broken links, code-block tags, citations and public-API coverage, reporting severity-ranked findings per page.
/perf-auditAudits an Apothem installation's per-class budgets (hooks, ecosystem verification, conformity gate, tests, agents, shell, lint) with its benchmark drivers, …
/security-auditAudits a repository's security posture: secrets, injection, unsafe deserialization, path traversal, vulnerable dependencies.
/supply-chain-auditAudits a repository's release pipeline: build provenance, artifact signing, SBOM completeness, pinned CI actions and minimum permissions.
/threat-model-auditThreat-models a repository with STRIDE per element and trust boundaries, classifying actors and rating residual risk.
/ux-reviewReviews a repository's developer experience from a first-time user's view: CLI ergonomics, error messages, install flow and docs discoverability.
/fortressHardens a repository end to end: runs the audit sweep, verifies each finding, remediates survivors through the surgical-guard, secret-rotation and vuln-triage …
/elevateWhole-repository elevation: runs the audit sweep, then critiques naming, structure, storytelling and extensibility, remediates what it finds (deletions are …
/evalRuns one evaluation campaign for a language model or prompt: scores each output over a dataset and reports metrics by category plus regressions against a …
/freshifyUse when a repository must be made fresh and release-clean: purges caches and stale artifacts, removes legacy narrative and back-references, normalizes file …
/github-deploy-freshUse when a GitHub repository needs one clean first release on origin/main: a single v0.1.0 release commit, green workflow cards, a first-version changelog, and …
/github-deploy-nextUse to run the next release cycle on a GitHub repository: merge ready pull requests, resolve the issues the release addresses, derive the SemVer bump from …
/projectifyBuilds the Description, Instruction and knowledge files for a chat-app Project or custom assistant through guided questions, within the platform's context …
/release-readinessPre-release gate sweep: use before shipping a repository to check lint, format, types, tests, dependency and supply-chain risk, visibility surfaces, changelog …
/test-suiteAuthors and runs behavior-first tests for a repository, triages failures and reports coverage gaps on critical paths.
/workflowUse to run a non-trivial mission as an independent multi-agent workflow: parallel subagents under named return contracts, refute-by-default verification of …

On this page