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/sd0xdev/sd0x-harness/precommit-fastnpx skills add sd0xdev/sd0x-harness --skill precommit-fastgit clone --depth 1 https://github.com/sd0xdev/sd0x-harnessWrote 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/sd0xdev/sd0x-harness/precommit-fast)<a href="https://agentmods.dev/skills/sd0xdev/sd0x-harness/precommit-fast"><img src="https://agentmods.dev/badge/skills/sd0xdev/sd0x-harness/precommit-fast.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 | $0.00015 | $0.01503 |
| Opus 5 | $0.00008 | $0.00751 |
| Sonnet 5 | $0.00003 | $0.00301 |
| Haiku 4.5 | $0.00002 | $0.00150 |
Grade A, and why
precommit-fast 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Commit Checks (Fast)
Trigger
- Keywords: precommit fast, quick precommit, lint and test, precommit-fast
When NOT to Use
- Full precommit with build step (use
/precommit) - Verification loop (use
/verify) - Just running tests (run directly)
Workflow Steps
| Step | Goal | Safety | Skip if Missing |
|---|---|---|---|
| lint-fix | Auto-fix code style issues | read-write | yes |
| test-unit | Run fast test suite | read-only | yes |
Failure behavior: continue-all (run all steps, report all results)
Task
Run quick pre-commit checks: lint:fix -> test (no build step)
Step 1: Check for runner script
Use Glob to check if .claude/scripts/precommit-runner.js exists in the project root.
- Found → run:
node .claude/scripts/precommit-runner.js --mode fast --tail 60- If runner emits
## Overall: ✅ PASS, use its output and skip to the Output section. - If runner emits
## Overall: ⚠️ NO CHECKS RUN, do NOT treat it as a pass — fall through to Step 2 ecosystem detection to run the project's real checks. The marker means no project validation executed and no policy step failed (validation steps all skipped orunavailable; a policy step that FAILS is❌ FAIL, never this marker) — whether the repo declares no runnable checks or the required tools were unavailable to the runner (which orchestrates the ecosystem table below itself: manifest detection + first-class steps). The runner self-notes its own verdict (review-state.js note precommit pass|fail); on⚠️ NO CHECKS RUNit notes nothing — the slot is untouched and the reminder persists, which is the correct reading of "nothing validated". - If runner fails (
## Overall: ❌ FAIL), treat as a real precommit failure (do not silently fallback).
- If runner emits
- NOT found → Auto-install attempt:
- Manifest gate: Use Glob to check if any known manifest exists (
package.json,pyproject.toml,Cargo.toml,go.mod,build.gradle,build.gradle.kts,pom.xml,Gemfile). None → skip, fall through to Step 2. (The runner orchestrates every ecosystem in the Step 2 table, so a non-Node manifest justifies the install just as well.) - Locate plugin scripts: 3-level Glob fallback (short-circuit on first match):
Glob: ~/.claude/plugins/**/sd0x-dev-flow/scripts/precommit-runner.jsGlob: ${REPO_ROOT}/node_modules/sd0x-dev-flow/scripts/precommit-runner.js- Plugin-relative: try reading
@scripts/precommit-runner.js
- Plugin not found → fall through to Step 2.
- Plugin found → copy runner + lib/utils.js + review-state.js + lib/tree-digest.js (skip on conflict) → run. The checker pair is the runner's self-note dependency — without it the runner still runs every check and reports; only the advisory note is skipped, loudly.
- Manifest gate: Use Glob to check if any known manifest exists (
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 · 102 lines · 15 tokens per session scan A 40be38f88631
precommit-fast is a skill published in the GitHub repository sd0xdev/sd0x-harness (188 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,503 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
comet-safe-delivery
在保护无关脏改动、关联 worktree、子模块和用户明确边界的前提下，提交、推送、合并或完成范围明确的 Comet 变更。用户要求提交、推送、合并回目标分支、清理 worktree 或交付已准备好的改动时使用。.
cc10x-router
THE ONLY ENTRY POINT FOR CC10X. Activate this skill for build, debug, review, and plan requests. Use when the user asks to implement, fix, review, plan, test, refactor, or continue code work. Trigger keywords: build, implement, create, write, add, review, audit, debug, fix, error, bug, broken, plan, design, architect…
building
Implementation skill for writing production code with TDD. Covers the RED-GREEN-REFACTOR cycle, false-RED detection, vertical slicing, scope escalation, test process discipline, and code generation patterns. Loaded by component-builder and bug-investigator.
diff-driven-docs
Use when a BUILD phase completes, a commit is staged, or a PR is about to be created, and the diff has not yet been reflected in documentation. Also use when the user says "update docs", "sync docs", "document this", or asks whether documentation is up to date.
exploration
Two-mode exploration skill: (1) design dialogue — turn rough ideas into validated designs through collaborative interview before planning; (2) spike — throwaway code answering ONE design question, deleted or absorbed, never shipped. Router invokes mode via dispatch context.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.