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/david405/harness-kit/create-pull-requestnpx skills add David405/harness-kit --skill create-pull-requestgit clone --depth 1 https://github.com/David405/harness-kitWhat 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 | $0.00070 | $0.00712 |
| Opus 5 | $0.00035 | $0.00356 |
| Sonnet 5 | $0.00014 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
create-pull-request 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create pull request
GitHub PRs are product-facing and detailed. A reviewer who has not seen the session should
understand the problem, the fix, what changed in behaviour, and how it was verified. Harness workflow
(contracts, FEATURES.json IDs, harness-review, audit finding codes) stays in local/session
context only.
Before opening
- Human explicitly asked to push and/or open a PR.
- VERIFY is green; harness review is done (reported in chat, not in the PR body).
- Run
git status,git diffvs the default branch,git logfor commits on the branch. - Draft the full body from the diff — do not ship a sparse PR.
Title format
Conventional commit style — no ticket/harness IDs:
<type>(<scope>): <what changed in plain English>
Do not include: feature ledger IDs (SEC-002, PAY-015), audit codes (AUDIT-001-F02),
PENDING_REVIEW, or contract file paths.
Body template (required sections)
Use all sections below. Omit a section only when truly N/A (say "N/A" in one line).
Template file: templates/pull_request_template.md (install to .github/pull_request_template.md
via setup-harness-kit.sh when missing).
## Summary
<2–4 sentences: what this PR does and why it matters.>
## Problem
<What was broken, unsafe, or missing — user-visible or production symptom.>
## Solution
<How the code fixes it. Key functions, routes, guards.>
## Behaviour changes
| Before | After |
|--------|-------|
| <old> | <new> |
## Files changed
- `path/to/file` — <one line each>
## Risk and rollout
- **Risk:** Low / Medium / High — <why>
- **Rollback:** <safe to revert?>
- **Prod / env notes:** <env vars, flags — or "None">
## Test plan
- [x] `<command>` — <result>
- [ ] CI build + e2e
Forbidden in title, body, and commit messages
- Feature ledger IDs, audit finding IDs, contract paths
- Sections named "Harness review", "Contract compliance", sprint contract paste
- Contract HTML markers (
<!-- harness-kit:contract:start -->) - Tool attribution (
Made with Cursor,Co-Authored-Byassistant)
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.
- yesterday First seen · 100 lines · 70 tokens per session scan A de9f3f354d69
create-pull-request is a skill published in the GitHub repository David405/harness-kit (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 70 tokens to every session and 712 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…