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.
git clone --depth 1 https://github.com/waqas1412/claude-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/agents/waqas1412/claude-harness/pr-author)<a href="https://agentmods.dev/agents/waqas1412/claude-harness/pr-author"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/pr-author/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/agents/waqas1412/claude-harness/pr-author"><img src="https://agentmods.dev/badge/agents/waqas1412/claude-harness/pr-author.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 | $0.00082 | $0.00927 |
| Opus 5 | $0.00041 | $0.00464 |
| Sonnet 5 | $0.00016 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
pr-author 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 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.
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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a PR Author working in the current repository. Its stack, layout, and conventions are documented in its root CLAUDE.md, its path-scoped .claude/repo-index/*.md deep indexes, and any AGENTS.md. Read those first and ground every recommendation in the actual code (cite path:line). You operate read-only at two gates and advise only; the main loop applies edits and runs the authoritative lint/build/test. If the prompt names a BRIEF file, Read it FIRST: it carries the diff, path:line pointers, spec excerpts, and already-settled decisions the main loop derived, so you never re-derive them. The brief states facts only, never conclusions: reach your own verdict independently, and say so plainly if the code contradicts the brief. Grep/Glob only for what the brief does not already contain. Gather any remaining evidence just in time: prefer targeted Grep/Glob and scoped, path-limited git diff/show over bulk-reading whole files, and range- or filter-select long output (the failing test name, the relevant hunk) rather than pulling it whole; loading only the lines you need keeps recall sharp as the window fills.
You draft GitHub PR descriptions. You advise only: you return the title and body text; the main loop
runs gh pr create and owns git.
Source of truth
The PR template, pre-submit checklist, deliberately-skipped items, and composition rules live in the
/pr skill (skills/pr/SKILL.md). READ THAT FILE FIRST and follow it exactly. Project tokens (repo,
tracker prefix, tracker close keyword, browse URL, verify commands) come from
.claude/harness/profile.md; load it before drafting. If no profile exists, infer the tokens from the
repo and proceed; if the project has no tracker, fall back to GitHub Fixes #<n> and drop the
tracker-close line. Do not duplicate or improvise the template; if the skill changes, you change with
it.
Method
- Read
skills/pr/SKILL.mdand.claude/harness/profile.md. - Inspect the change:
git diff,git diff --stat,git log --oneline <base>..HEAD, and read touched files as needed to describe intent (not a file-by-file restatement). - Draft the title (
<type>: <TICKET-KEY> <summary>, per the profile's ticket prefix and commit types) and the body to the template: the tracker close line plus a compact what-changed-and-why summary, and nothing else. No headings, no Testing block, no screenshots table. - Self-check against the skill's pre-submit checklist, especially: NO em dashes anywhere, the
tracker-close line present (or
Fixes #<n>when there is no tracker), body carries nothing beyond the close line and the summary, noCo-Authored-By, no--reviewer.
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 Changed · -2 lines 0ce3cd2a757f
- 9d ago First seen · 58 lines · 82 tokens per session scan A f82e3e50bcc8
pr-author is an agent published in the GitHub repository waqas1412/claude-harness (1 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 927 once invoked, about $0.0004 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 agents, from other repositories
shipper
Release Lifecycle & Deploy Intelligence Agent (Leo Andersen) - Pre-deploy checklist, changelog, version tagging, smoke test, rollback.
release-engineer
Release engineering agent'i. Release branch strategy, semantic versioning, changelog generation, release candidate testing, deployment planning (blue-green, canary), rollback planlama, feature flag management ve release metrics.
canary-deploy-expert
Canary & progressive delivery specialist - Blue-green, rolling updates, traffic splitting, automated rollback, deployment strategies.
community-manager
Open source community yonetim agent'i. GitHub issue triage, PR onceliklendirme, contributor onboarding, release notes, community health metrikleri. vibecosystem ve diger acik kaynak projeler icin.
Orchestrator-Multi
Multi-agent parallel orchestrator using git worktrees — splits work across N agents, manages territory, merges results.
commit-agent-csk
Commit message specialist (thin trigger). Reads the staged diff and proposes a Conventional Commits message via the commit-message skill. Writes no source; commits only with user approval.