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/yu-iskw/coding-agent-fabric/clean-projectnpx skills add yu-iskw/coding-agent-fabric --skill clean-projectgit clone --depth 1 https://github.com/yu-iskw/coding-agent-fabricWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/yu-iskw/coding-agent-fabric/clean-project)<a href="https://agentmods.dev/skills/yu-iskw/coding-agent-fabric/clean-project"><img src="https://agentmods.dev/badge/skills/yu-iskw/coding-agent-fabric/clean-project.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00042 | $0.00382 |
| Opus 5 | $0.00021 | $0.00191 |
| Sonnet 5 | $0.00008 | $0.00076 |
| Haiku 4.5 | $0.00004 | $0.00038 |
Grade C, and why
clean-project scanned grade C with 1 finding 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 5d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Recursively delete `node_modules`: `find . -name "node_modules" -type d -prune -exec rm -rf '{}' +`. This is a copy
100% identical to clean-project — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Clean Project (Hard Reset)
This skill provides a destructive but thorough way to repair a "broken" development environment by removing all cached artifacts and re-initializing from scratch.
When to Use
pnpm installfails repeatedly with checksum or resolution errors.trunkreports internal errors that persist aftertrunk install.- "Ghost" errors occur (failures that don't match the current code).
Workflow
-
Clean Dependencies:
- Recursively delete
node_modules:find . -name "node_modules" -type d -prune -exec rm -rf '{}' +. - Remove global lockfile:
rm pnpm-lock.yaml.
- Recursively delete
-
Clean Tooling Cache:
- Clear Trunk cache:
trunk clean. - Prune pnpm store:
pnpm store prune.
- Clear Trunk cache:
-
Re-initialize Environment:
- Invoke the
setup-dev-envskill to reinstall everything.
- Invoke the
-
Verify Health:
- Invoke the
verifiersubagent (../../agents/verifier.md) to ensure the project is back to a clean, working state.
- Invoke the
Safety Note
This process is destructive to the local environment but safe for the repository. It will require a full download of all dependencies, which may take several minutes depending on network speed.
Resources
- pnpm Commands for Node.js: Common pnpm maintenance commands.
- Trunk CLI Reference: Commands for managing Trunk artifacts.
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.
- 5d ago First seen · 40 lines · 42 tokens per session scan C 6a99a28527ad
clean-project is a skill published in the GitHub repository yu-iskw/coding-agent-fabric (1 stars, last pushed 5d ago), licensed Apache-2.0. It adds 42 tokens to every session and 382 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 100% identical to clean-project, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
firebase-crashlytics
Use when implementing crash reporting, capturing fatal/non-fatal errors, recording isolate/async exceptions, customizing reports, or uploading obfuscated symbols.
flutter-errors
Use when hitting layout errors (RenderFlex overflow, unbounded constraints, RenderBox not laid out), scroll errors, or setState-during-build errors.
fix
修复者 — 把一条被发现的问题（finding）按它的闭合合约修干净，修一个不制造下一个。产 FixProposed + 临时的 FixCompleted，不自判问题关闭（那是复查的权）。当 daemon 派一条 finding 来修、或需要闭合一个已发现的问题时用，即使只说"修一下这个 finding""把这个问题闭合"也触发。调用名就是 fix（Skill 工具）或 /fix（命令），没有 harness: 之类的前缀。.
code-context
How to answer codebase questions with the code-context MCP tools (search, sql, reindex): ranked hybrid keyword+semantic search, relevance-ranked SQL aggregation over the index, and index lifecycle. Use when a question spans many files ("how does X work", "where is Y handled"), when ranking or counting code by topic…
support-ticket-triage
Triage support tickets by pulling helpdesk context, searching issue trackers and knowledge bases in parallel, classifying the issue, and giving reps a recommended next action.
bug-evidence-protocol
Capture and classify minimal red-to-green evidence for a diagnosed bug and scoped fix, with command hashes, Git/environment identity, broader-check records, risk-based approval, route evidence, and optional cpat linkage. Use after diagnose establishes a credible reproducer or when a reported regression needs an…