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/fiveonecode/agent-skills/harness-engineeringnpx skills add fiveonecode/agent-skills --skill harness-engineeringgit clone --depth 1 https://github.com/fiveonecode/agent-skillsWhat 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 | $0.00067 | $0.00924 |
| Opus 5 | $0.00034 | $0.00462 |
| Sonnet 5 | $0.00013 | $0.00185 |
| Haiku 4.5 | $0.00007 | $0.00092 |
Grade A, and why
harness-engineering 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 2d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Engineering
Overview
Use this skill to translate harness engineering principles into concrete repository changes that improve agent speed, correctness, and maintainability.
Workflow
1) Assess the current harness
- Inspect
AGENTS.md, contributor docs, CI workflows, and repo scripts. - Map the actual path from prompt to merged change.
- List concrete failure modes: ambiguous instructions, repeated mistakes, slow reviews, merge conflicts, stale docs, or noisy CI.
2) Define operating boundaries
- Separate decisions by layer:
- Human layer: architecture, taste, policy, and final risk acceptance.
- Agent layer: implementation, refactors, test updates, and routine maintenance.
- Define non-negotiable constraints before coding starts:
- Required tests and linters.
- Directory ownership and file-scoping rules.
- Branch, PR, and commit conventions.
3) Make the repository the system of record
- Encode process in files, not tribal knowledge.
- Prefer deterministic entry points:
- Single source for setup.
- Canonical command wrappers (
make,just, or scripts). - Stable templates for PRs, issues, and specs.
- Remove conflicting guidance and duplicate docs.
4) Increase agent legibility
- Prefer one clear pattern over many equivalent ones.
- Standardize naming, folder layouts, and module boundaries.
- Add concise examples for fragile tasks.
- Eliminate hidden behavior and implicit coupling.
5) Add mechanical guardrails
- Enforce checks automatically:
- Fast local checks for iteration.
- CI gates for merge readiness.
- Static analysis for known failure classes.
- Fail with actionable messages that point to exact fixes.
- Keep checks strict enough to prevent regressions, but fast enough for daily use.
- For any verifier or generated QA artifact, check verifier integrity before trusting a pass result.
6) Optimize merge throughput
- Encourage smaller, composable changes instead of large batches.
- Isolate independent work streams to reduce collisions.
- Define explicit integration rules for overlapping files.
- Prefer rapid merge and follow-up fixes over long-lived divergence.
What ships with it
2 files 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.
- 2d ago First seen · 98 lines · 67 tokens per session scan A 7ce618a09328
harness-engineering is a skill published in the GitHub repository fiveonecode/agent-skills (19 stars, last pushed 10d ago), licensed MIT. It adds 67 tokens to every session and 924 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 2026-08-30.
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…