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 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/plan)<a href="https://agentmods.dev/skills/vasuag09/harness-claude/plan"><img src="https://agentmods.dev/badge/skills/vasuag09/harness-claude/plan.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 | $0.00044 | $0.00760 |
| Opus 5 | $0.00022 | $0.00380 |
| Sonnet 5 | $0.00009 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
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 8d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan — phased implementation plan
Goal: a plan an executor (you or a subagent) can follow without re-deriving context.
Do this
- For non-trivial work, delegate to the
harness-claude:planneragent, passing it the spec (read.claude/planning/<slug>/SPEC.mdif present — the slug is in.claude/STATE.md), the reuse decision, and the objective/purpose (not just a one-line query). - For small/linear work, plan inline using the same shape.
- Break work into phases/tasks: each small, independently verifiable, with an exit check.
Give each task an ID (
T1,T2, …), its write-set (files it will create/edit), adepends_onlist of prior task IDs, and theAC-ncriteria it addresses — the format/harness-claude:orchestrateand/harness-claude:verifyconsume (schema:docs/state-and-artifacts.md). - Surface risks, dependencies, and ordering explicitly. Red-team the plan before
handing it off — assume it already failed and ask why; attack your own draft for
hidden assumptions and missing edge cases, not just the obvious risks. Note where
you'll need an architecture decision (
/harness-claude:architect) vs. where the path is obvious. - Flag parallelizable phases. From the per-phase file lists, mark any phase that writes
3+ independent files with disjoint write-sets and no cross-dependency as an
/harness-claude:orchestratecandidate. This is what makes/implementsurface the parallel fan-out offer instead of silently editing serially — if you don't flag it here, it's usually missed there. Flag only genuine cases; if none qualify, say so.
Output
For non-trivial work, write .claude/planning/<slug>/PLAN.md (present a summary in the
reply too); for trivial work, the plan in the reply is enough (say so). Format:
## Plan: <title>
## Tasks
### Task T1: <goal>
- files: <write-set>
- depends_on: []
- addresses: AC-1, AC-2
- exit check: <test/build/behavior>
### Task T2: ...
## Risks & dependencies
## Parallelizable phases (if any) — tasks with 3+ independent files, disjoint write-sets → /orchestrate candidates
## Where /architect is needed (if any)
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.
- 8d ago First seen · 60 lines · 44 tokens per session scan A 1ba0f282f492
plan is a skill published in the GitHub repository vasuag09/harness-claude (2 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 760 once invoked, about $0.0002 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…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
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.
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.