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 vasuag09/harness-claude --skill harness-implementgit clone --depth 1 https://github.com/vasuag09/harness-claudeWrote 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/vasuag09/harness-claude/harness-implement)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/harness-implement"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/harness-implement.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00569 |
| Opus 5 | $0.00031 | $0.00284 |
| Sonnet 5 | $0.00012 | $0.00114 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
harness-implement 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 7d 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.
What it actually says
/harness-implement — run the Implement phase
Thin orchestrator over the Implement skills. Requires an approved plan from
/harness-claude:harness-plan (or /harness-claude:plan). Refuse to start without one for non-trivial work.
Sequence
-
For each plan phase, in order:
/harness-claude:implement— delegate to theharness-claude:tdd-guideagent: failing test (RED) → minimum code (GREEN) → refactor, against the phase's acceptance criteria.- Parallel-fan-out checkpoint (mandatory when it triggers): before editing a phase
serially, if it spans 3+ independent files with disjoint write-sets and no dependency, you
must surface
/harness-claude:orchestrate— name the file split and let the user choose. The offer is not optional (that's the only way parallel mode fires); acting on it stays opt-in — never auto-start a multi-agent run. - Let the format/typecheck/quality hooks run; act on what they surface.
- If the build/types break and the fix isn't obvious →
/harness-claude:build-fix(delegate to theharness-claude:build-error-resolveragent), minimal diffs only. - Confirm the phase's exit check (tests green, build clean) before the next phase.
-
Plan-divergence gate: if reality contradicts the plan (a phase is wrong, missing, or bigger than scoped), HALT — report the divergence, update the plan with the user, then resume. Never silently improvise scope.
Rules
- Delegate search/exploration and isolated edits to cheaper models; keep the orchestrator focused on integration.
- Files stay modular and lean (<800 lines), immutable patterns, validated inputs.
- Compact at phase boundaries, not mid-phase.
- Do not commit or push — branch creation follows
rules/git.md(branch-at-first-write in/harness-claude:implement).
Output
Phase-by-phase summary (what was built, tests added, build status). Then hand off to
/harness-claude:harness-verify.
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.
- 7d ago First seen · 41 lines · 62 tokens per session scan A 605b56dd63b6
harness-implement is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 62 tokens to every session and 569 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
ci-tests
Run the test suite for the current repo, auto-detecting Python (pytest/uv), Node (vitest/pnpm), or Rust (cargo test).
tdd-workflow
Enforce practical Test-Driven Development for code changes in Go services. Use for new features, bug fixes, refactors, API changes, and new modules. Requires Red-Green-Refactor evidence, defect-hypothesis-driven tests, killer cases, and coverage gates (line + risk-path).
git-worktree
Create isolated git worktrees for feature development without switching branches.
tdd
Use when building any T3 feature or bugfix, recommended for T2 on the affected path — write the failing test before the implementation, one behavior at a time, through public interfaces.
git-worktree-status
Check status of background verification tasks running in a git worktree.
testing
Use when implementing any feature or bugfix - before writing implementation code. Write the test first, watch it fail, then implement.