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/corteshvictor/vichu-flow/commitnpx skills add corteshvictor/vichu-flow --skill commitgit clone --depth 1 https://github.com/corteshvictor/vichu-flowWhat 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 | $0.00103 | $0.01226 |
| Opus 5 | $0.00051 | $0.00613 |
| Sonnet 5 | $0.00021 | $0.00245 |
| Haiku 4.5 | $0.00010 | $0.00123 |
Grade A, and why
commit 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 2d ago.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Branch, Commit & PR Skill (VichuFlow)
Three workflows: creating branches, creating commits, and opening pull requests.
All follow Conventional Commits v1.0.0, matching the linter in
.github/workflows/pr-title.yml and the changelog config in
release-please-config.json.
Activation guardrail (mandatory)
Use this skill only when the user explicitly asks for a git mutation in the current turn (branch, stage, commit, push, or PR). Never infer permission from workflow progress, "ready" states, or any other contextual signal.
Hard rules (never break)
- NEVER add a
Co-Authored-Bytrailer or any AI/assistant attribution. Commits are authored solely by the user. No exceptions. - Stage specific files by name — never
git add -Aorgit add .. They can pull in machine-local files (.agents/settings.local.json,.env, credentials) or build artifacts. - Write all git artifacts in English (subject, body, footer, PR title, PR body, branch names) even when the chat is in Spanish. This keeps history consistent; it does not affect chat replies.
Conventional Commits
Format: <type>(<optional scope>): <description>
| Rule | Value |
|---|---|
| types | feat, fix, perf, revert, refactor, docs, style, test, build, ci, chore |
| type/scope case | lower-case |
| subject | required, imperative mood, no trailing period |
| header length | ≤ 100 chars |
| breaking change | ! after type/scope (feat(engine)!: ...) or BREAKING CHANGE: footer |
Scopes (optional) reference the affected package: engine, runtime,
security, adapters, config, workflows, cli. Omit if changes span many.
Choosing the type: feat new capability · fix bug fix · perf performance
· refactor no behavior change · style formatting only · docs docs only ·
test tests · build build/deps · ci CI config · chore tooling/maintenance
· revert revert a prior commit.
Pre-1.0 version impact (via release-please): feat→minor, fix/perf→patch,
breaking→minor, everything else→none.
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.
- 2d ago First seen · 117 lines · 103 tokens per session scan A 8be7badca962
commit is a skill published in the GitHub repository corteshvictor/vichu-flow (5 stars, last pushed 1mo ago), licensed MIT. It adds 103 tokens to every session and 1,226 once invoked, about $0.0005 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
atelier
Operate the Atelier software factory (the ADW engine stamped into this repo's adws/). Use when the user says /atelier, wants to create / run / update an ADW or workflow, manage the agent roster in sssf.config.yaml, keep the engine current, or observe running agent workflows. Keywords - atelier, software factory, ADW…
release
Cut an Atelier release end to end - decide the version bump, branch, commit, open the PR, wait for CI, squash-merge, tag, and publish the GitHub release. Use when the user says "create a release", "finalise the release", "cut a release", "ship this", "tag a release", or "bump the version". Keywords - release, cut a…
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…
tutti-test-audit
Audit, design, write, materially revise, or remove Tutti tests. Use whenever Codex changes or reviews unit, component, conformance, integration, regression, platform, or repository tests; enforce a protected product contract, credible failure, correct owning boundary, negative-control evidence, overlap review…
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
babysit-babysitter-issues
This skill should be used when the user asks to "babysit issues", "work on assigned issues", "check a5c-agent issues", "process babysitter issues", or wants to find and work on open GitHub issues assigned to a5c-agent in the babysitter repo.