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-plangit 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-plan)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/harness-plan"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/harness-plan/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/vasuag09/harness-claude/harness-plan"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/harness-plan.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 | $0.00064 | $0.00791 |
| Opus 5 | $0.00032 | $0.00396 |
| Sonnet 5 | $0.00013 | $0.00158 |
| Haiku 4.5 | $0.00006 | $0.00079 |
Grade A, and why
harness-plan 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 12d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/harness-plan — run the Plan phase
A thin orchestrator. It does not re-implement the sub-skills; it sequences them,
enforces the gates, and stops for you at real decision points. Keep using the atomic
skills (/harness-claude:spec, /harness-claude:plan, ...) directly when you only want one step.
Sequence
-
/harness-claude:spec— clarify the request into a spec with testable acceptance criteria. → HALT and ask the user any load-bearing clarifying questions. Do not proceed on guesses. Resume once the spec's open questions are resolved. -
/harness-claude:research— reuse-first search (in-repo → context7 → registries/GitHub → web). Produce the build-vs-reuse decision; fold it into the spec. -
/harness-claude:plan— delegate to theharness-claude:planneragent (pass it the spec + reuse decision + the objective, not just a query). Return a phased plan (tasks with write-sets +depends_on+ theAC-neach addresses) with per-task exit checks. -
/harness-claude:plan-check— gate the plan against the spec (criteria coverage, scope, parallel-task disjointness) before any code. Delegate to theharness-claude:planneragent in a read-only check pass. Loop ≤3 revisions with/harness-claude:planon findings. → HALT and show the user the checked plan for approval before any code. A standing Critical finding blocks the phase. -
Design gate — two independent, conditional siblings. A change can need one, both, or neither; run only what's relevant and say which you skipped.
/harness-claude:architect— only if the plan flagged a load-bearing system decision (new subsystem, public interface/data model, cross-cutting change, multi-shape refactor). Delegate to theharness-claude:architectagent and present the ADR./harness-claude:design— only if the change has a user-facing surface (page, screen, component, form, mobile, CLI/TUI presentation). Produce the design brief. → HALT for approval on whichever ran. If the work is routine and internal (no UI, no load-bearing design — like this CLI harness itself), skip both and say so.
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.
- 12d ago First seen · 51 lines · 64 tokens per session scan A 913dcab60754
harness-plan is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 791 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
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
issue-triage
3-phase issue backlog management with audit, deep analysis, and validated triage actions. Use when triaging GitHub issues, sorting bug reports, cleaning up stale tickets, or detecting duplicate issues. Args: 'all' to analyze all, issue numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit only.
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.