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 Ancienttwo/repo-harness --skill claude-plangit clone --depth 1 https://github.com/Ancienttwo/repo-harnessWrote 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/ancienttwo/repo-harness/claude-plan)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/claude-plan"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/claude-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/ancienttwo/repo-harness/claude-plan"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/claude-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00128 | $0.03004 |
| Opus 5 | $0.00064 | $0.01502 |
| Sonnet 5 | $0.00026 | $0.00601 |
| Haiku 4.5 | $0.00013 | $0.00300 |
Grade A, and why
claude-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 10d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-plan — independent plan from Claude's plan mode
The host model planning its own work shares its own blind spots. A
different-vendor model (Anthropic Claude, pinned to Fable) has a different
training distribution, so where its plan diverges from yours is exactly where
to dig. This skill runs the Claude Code CLI (claude -p) in Claude's native
plan mode — read-only at the permission layer, with Claude's internal
research-then-plan steering — and presents the plan verbatim.
The consult is stateless: Claude cannot see the host session transcript. Everything it needs must travel in the decision brief. If you cannot write the brief, the question is not ready to be asked — that filter is a feature.
When to use
- Mid-execution, a design fork appears that the host should not settle unilaterally (irreversible structure, cross-module contract, risky migration).
- A high-stakes decision needs a cross-vendor second plan before committing.
When NOT to use
- Routine planning: use the host's own plan tooling (Codex Plan mode, /think).
- Planning known before the task starts: plan in a Claude session directly and hand off via a file-backed plan; do not call back mid-run.
- Anything answerable by reading the repo for five minutes.
Fable shares the main Claude quota pool — every consult is a full session. One consult per fork; do not iterate plans through repeated calls.
Step 0 — Preflight (binary)
command -v claude >/dev/null 2>&1 || {
echo "[claude-plan] Claude Code CLI not found. Install from https://claude.com/claude-code (then sign in). Skipping."
exit 0
}
If this prints the skip message, tell the user Claude Code is not installed and stop.
Step 1 — Compose the decision brief
Write the brief yourself (the host orchestrator), with every section filled concretely. The brief follows the shared architect consultation packet shape, so the same packet can be sent unchanged to any other external consultation track. Claude may read repository files for context, so cite paths instead of pasting whole files; paste only short excerpts or a scoped diff when the relevant state is not on disk.
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.
- 10d ago First seen · 272 lines · 128 tokens per session scan A 2b095e41b4ba
claude-plan is a skill published in the GitHub repository Ancienttwo/repo-harness (431 stars, last pushed today), licensed MIT. It adds 128 tokens to every session and 3,004 once invoked, about $0.0006 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
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-plan-refactor
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-implement-story
Implement a brownfield story with OpenLore orientation, risk checks, spec validation, tests, and drift detection. Use when asked to implement or continue a story in an existing codebase.
openlore-write-tests
Write and run real tests for a function or spec scenario after reading implementation and contract evidence. Use when asked to add, improve, or repair tests without stubs or placeholders.