Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/raintr91/processkit/business-process-tracenpx skills add raintr91/Processkit --skill business-process-tracegit clone --depth 1 https://github.com/raintr91/ProcesskitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.00951 |
| Opus 5 | $0.00016 | $0.00476 |
| Sonnet 5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00003 | $0.00095 |
Grade A, and why
business-process-trace scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/business-process-trace — Brownfield business process
Trace an observed end-to-end business process through legacy/code evidence.
Do not invent missing hops. Curated product journeys stay under /journey (FLOW-*).
Owner: Processkit · Accelerators optional: CodeGraph · Docskit · ArtifactGraph
Modifiers (If /legacy is used)
Khi gọi kèm /legacy (vd: /legacy /business-process-trace):
- Toàn bộ quá trình truy vết (trace) sẽ mặc định hướng về hệ thống cũ.
- Tham chiếu source code từ
legacy-repos.local.json. - Ghi nhận evidence với tư cách là "tài liệu khảo cổ", không dùng để build tính năng mới trực tiếp.
Load
| Load | Skip |
|---|---|
| Progressive map read (needed keys only) | Treating FE docs as architecture SSOT |
| Cross-repo route/job/event evidence | Writing new product FLOW-* without evidence |
Step vocabulary in extract business-process-trace.md |
Full platform-repos.json / .local.json dump |
Checkout resolution
For each step [system]:
| System id | Map |
|---|---|
legacy-* (or clear legacy archaeology) |
legacy-repos.local.json |
| Otherwise (live portal/api/tests/…) | platform-repos.local.json |
In-repo-only traces need no map. Cross-repo with missing/empty .local.json or
missing key → Gaps + handoff /configure-repo-maps (do not guess paths;
do not bypass an empty map). After maps exist, remind
platform-dna codegraph:wire if codegraph-<key> is absent. Ambiguous matches
→ ask the user or Gaps.
Workflow
- Discover entrypoint(s): page / API / webhook / command / schedule / job.
- Trace steps:
page | api | call | persist | job | event | listener | command | mail. - Per step record: system/repo, route/symbol, input/output, sync/async, evidence location.
- Mark unverified hops and process gaps; never invent missing calls.
- Handoff to
/journeyonly when promoting a curated target journey; handoff to/legacy-specfor module IR.
Accelerators (optional)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 90 lines · 33 tokens per session scan A d8809075a7bc
business-process-trace is a skill published in the GitHub repository raintr91/Processkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 951 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…