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 commands/costajohnt/oss-autopilot/plan-readygit clone --depth 1 https://github.com/costajohnt/oss-autopilotWrote 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/commands/costajohnt/oss-autopilot/plan-ready)<a href="https://agentmods.dev/commands/costajohnt/oss-autopilot/plan-ready"><img src="https://agentmods.dev/badge/commands/costajohnt/oss-autopilot/plan-ready.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 | $0.00030 | $0.00940 |
| Opus 5 | $0.00015 | $0.00470 |
| Sonnet 5 | $0.00006 | $0.00188 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
plan-ready 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 6d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/plan-ready
Drives the plan-review convergence loop that catches design-level
problems before any code is written. Mirrors /pr-ready exactly, but
applied to a plan artifact instead of a diff (#1249).
When to use
Run after you have completed investigation and written an implementation plan, BEFORE you start implementing. A solid plan caught and refined here is much cheaper than the same problem caught after 200 lines of code exist.
The slash command auto-locates the plan artifact at
/tmp/oss-autopilot-plans/<repo>-<issue-number>.md. Pass the path
explicitly if the plan lives elsewhere: /plan-ready /tmp/some-plan.md.
What it does
For the named plan artifact:
-
Verify the plan is complete enough to evaluate. Check that it has sections covering: investigation findings, proposed approach, specific file-level changes, alternative approaches considered, and acceptance criteria. Block readiness if the plan is a stub (single paragraph, no structure) — that needs more drafting before review.
-
Dispatch the pr-review-toolkit agents in parallel against the plan text:
pr-review-toolkit:code-reviewer— design-level critique (does the proposed approach make sense for the codebase? Are there simpler / more idiomatic alternatives the plan missed?)pr-review-toolkit:silent-failure-hunter— does the plan name how it handles edge cases, error paths, partial failures, or does it silently assume the happy path?pr-review-toolkit:code-simplifier— is the plan's scope right? Is there a simpler change that achieves the same outcome?devils-advocate— actively try to break the plan. List scenarios where the proposed approach fails or surprises a future reader.
Brief each agent with the plan text, the issue body it targets, and any contributing-guidelines context already discovered.
-
Triage findings:
- Critical findings (plan is wrong / incomplete in a way that would force a rewrite mid-implementation): block readiness.
- Recommended findings (plan ships but is suboptimal — wrong file structure, missed alternative): block readiness.
- Minor findings (wording, sectioning): report but don't block.
- Out-of-scope findings: list as "deferred to follow-up plan".
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.
- 6d ago First seen · 93 lines · 30 tokens per session scan A 0a094c2564fe
plan-ready is a command published in the GitHub repository costajohnt/oss-autopilot (12 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 940 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 2026-08-30.
Other commands, from other repositories
loci-scan
Refresh the current project's local Loci memory.
doc
Use this command to create a new feature doc, how-to, concept, reference, or troubleshooting guide — it scaffolds the file, frontmatter, structure, and sidebar entry.
claude-tracker
List and browse your saved Claude Code sessions with status (running/inactive/VS Code).
gov-reuse
Discover reusable UK government code before building from scratch.
INDEX
16 custom slash commands in /.claude/commands/.
test
Run tests with intelligent package filtering and reporting.