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 waqas1412/claude-harness --skill prgit 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/skills/waqas1412/claude-harness/pr)<a href="https://agentmods.dev/skills/waqas1412/claude-harness/pr"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-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/waqas1412/claude-harness/pr"><img src="https://agentmods.dev/badge/skills/waqas1412/claude-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 | $0.00050 | $0.01278 |
| Opus 5.5 | $0.00020 | $0.00511 |
| Sonnet 5.5 | $0.00010 | $0.00256 |
| Haiku 4.5 | $0.00005 | $0.00128 |
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 16d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR description (house standard, profile-driven)
First, load .claude/harness/profile.md for this project's tokens (REPO, TICKET_PREFIX,
TRACKER_BROWSE_URL, TRACKER_CLOSE_KEYWORD, DEFAULT_BRANCH, COMMIT_TYPES, LINT_CMD,
UNIT_TEST_CMD, E2E_TEST_CMD, BUILD_CMD). In a multi-repo profile the four command tokens are
the per-repo table's Lint / Test / Build / E2E columns for the repo you are in, and - there means the
step genuinely does not exist. If no profile exists, infer from the repo
(run /harness-init to create one) and proceed; if there is no tracker, use GitHub Fixes #<n> and
drop the tracker-close line.
Title (goes in GitHub's title field, NOT the body)
<type>: <TICKET-KEY> <imperative one-line summary>
- type is one of
COMMIT_TYPES(default: feat | fix | refactor | chore | perf | docs | test). - Append
!for a breaking change (e.g.feat!: <TICKET-KEY> ...). Optional module scope:feat(area): .... <TICKET-KEY>usesTICKET_PREFIX(e.g.PROJ-1234); omit if the project has no tracker.- Must stand alone in history; never "fix", "updates", "phase 1".
Body
The body is a tracker close line plus a compact summary of what changed and why. Nothing else: no section headings, no Testing block, no Screenshots table, no breaking-changes assertion, no notes-for-review.
Bullets are the shape, not a paragraph: 3 to 6 short bullets, one line each, each naming a change and its why. Fall back to a single sentence only when the change is genuinely one idea and a lone bullet would look odd. Never a wall of prose, and never a file-by-file restatement.
The close line is a link: <TRACKER_CLOSE_KEYWORD> [<TICKET-KEY>](<TRACKER_BROWSE_URL><TICKET-KEY>).
When there is no ticket, open the body with the source thread as a link instead. When the work came
from someone's report, close the body with Reported by <name> in [#channel](<url>).
A body describes the head it is on. Whenever a commit lands, the scope moves, or review feedback lands, reconcile the body in the same step rather than leaving it describing an older head.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 16d ago Changed · +50 tokens per session d94cd79cb3db
- 1mo ago Changed · +12 lines da18be8c5e1f
- 1mo ago Changed · +15 lines · -103 tokens per session 972c1bef390e
- 1mo ago First seen · 42 lines · 103 tokens per session scan A 08e91f018003
pr is a skill published in the GitHub repository waqas1412/claude-harness (2 stars, last pushed 17d ago), licensed MIT. It adds 50 tokens to every session and 1,278 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
review
Use when operating as the Fabrik Review stage agent. This skill guides code review of an implementation, finding and fixing issues, and ensuring the PR is ready for human review.
review-comment
Use when operating as the Fabrik Review comment reviewer. This skill guides applying user decisions on review findings — fixing issues, dismissing false positives, or deferring items — then committing and pushing without signaling stage completion.
gh-pr
Create, review, or manage GitHub pull requests. Use when asked to open, check, or merge a PR.
github-pr-workflow
GitHub PR lifecycle: branch, commit, open, CI, merge.
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
babysit
Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.