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 skills add Bradymck/claude-code-harness --skill prgit clone --depth 1 https://github.com/Bradymck/claude-code-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/bradymck/claude-code-harness/pr)<a href="https://agentmods.dev/skills/bradymck/claude-code-harness/pr"><img src="https://agentmods.dev/badge/skills/bradymck/claude-code-harness/pr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bradymck/claude-code-harness/pr"><img src="https://agentmods.dev/badge/skills/bradymck/claude-code-harness/pr.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00060 | $0.00622 |
| Opus 5.5 | $0.00024 | $0.00249 |
| Sonnet 5.5 | $0.00012 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
pr 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 1mo 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Workflow
Enforce complete git hygiene before opening any PR. Never skip a step.
Steps (execute in order, stop and fix before continuing)
1. Verify git identity
git config user.name
git config user.email
Must match the identity you intend to commit as. If wrong:
git config user.name "<your-github-username>"
git config user.email "<your-email>"
2. Check what's changed
git status
git diff --stat
List every modified file. Do NOT skip unstaged files.
3. Run the build
Run the project's build command (check package.json scripts, Makefile, or CI config):
- Node projects:
npm run build(or the project's equivalent) - Python:
python3 -m py_compile <entrypoint>or the project's test/lint command - TypeScript:
npx tsc --noEmitat minimum
Fix any errors before continuing. Do not open a PR with a broken build.
4. Stage ALL changed files
git add <every modified file by name>
Never use git add -A or git add . (risk of committing secrets or binaries).
Double-check with git status — nothing should show as unstaged.
5. Create a feature branch if not already on one
git checkout -b <descriptive-branch-name>
Never commit directly to main. Branch names: feat/, fix/, chore/.
6. Commit
git commit -m "<type>(<scope>): <description>"
Follow conventional commits. No --no-verify.
7. Push
git push -u origin <branch>
Verify the remote is the correct account (gh repo view to confirm).
8. Create PR
gh pr create --title "<title>" --body "$(cat <<'EOF'
## Summary
- <bullet points of what changed>
## Test plan
- <what to verify>
🤖 Generated with Claude Code
EOF
)"
9. Return the PR URL
Share the PR link with the user so they can review before merging.
Rules
- NEVER merge or deploy without user approval
- NEVER use
--forcepush to main - NEVER skip the build check — a broken build is worse than no PR
- If pre-commit hook fails, fix the issue and create a NEW commit (never
--amend)
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.
- 1mo ago First seen · 90 lines · 60 tokens per session scan A 55cd53637799
pr is a skill published in the GitHub repository Bradymck/claude-code-harness (3 stars, last pushed 4mo ago), licensed MIT. It adds 60 tokens to every session and 622 once invoked, about $0.0002 per session on Opus 5.5. 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
working-in-worktrees
Decides when agent work needs an isolated git worktree and how to create, enter, and clean one up safely. Use when starting code changes in a checkout that may be shared with another agent, dispatching a Linear task, executing a spec, or running any parallel work that mutates tracked files.
writing-changelogs
Writes human-friendly changelog entries and release notes. Use when populating changelog, preparing releases, or reviewing release notes quality.
ci-local-export
Daily CI Steward job: export this clone's git hook timings (how long git commit and git push took, and which pushes were killed at the tool ceiling) to the ci-steward-data branch, then trim the local timings file. A DorkOS scheduled skill that runs pnpm ci:local-export.
deps-weekly
Monday DorkOS dependency upkeep, called from @dorkos-qa's heartbeat: runs /app:upgrade unattended in a throwaway worktree, lands one PR per lane, files tickets for majors, and posts one line to @dorkos-pm. Never bumps the runtime SDKs (that is runtime-watch). Use only when a heartbeat checklist or a person asks for…
code-review-loop
Iterative review+fix loop for BASESHA..HEAD: generate findings, apply accepted fixes, run checks, commit, and re-review up to 3 iterations or until clean.
dedup
Dedupe-only pass for BASESHA..HEAD: remove duplicate code introduced by the diff or reuse existing shared utils; applies changes + commits.