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 lwalden/AIAgentMinder --skill revisegit clone --depth 1 https://github.com/lwalden/AIAgentMinderWrote 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/lwalden/aiagentminder/revise)<a href="https://agentmods.dev/skills/lwalden/aiagentminder/revise"><img src="https://agentmods.dev/badge/skills/lwalden/aiagentminder/revise.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 | $0.00015 | $0.01403 |
| Opus 5 | $0.00008 | $0.00701 |
| Sonnet 5 | $0.00003 | $0.00281 |
| Haiku 4.5 | $0.00002 | $0.00140 |
Grade A, and why
revise 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aiagentminder:revise - Revise the Plan
Revise the project plan (docs/strategy-roadmap.md) from new information, research findings, or changed requirements — the product-owner feedback point. Synthesize updates directly into the planning documents.
Unlike /aiagentminder:brief (which creates the plan from scratch), /aiagentminder:revise modifies an existing plan: lightweight and conversational, not a multi-round interview.
Before Starting
Read these files to understand the current plan:
docs/strategy-roadmap.md— the living planDECISIONS.md— architectural decisions and known debtSPRINT.md(if it exists) — active sprint state
If docs/strategy-roadmap.md doesn't exist or is still placeholder, tell the user: "No roadmap found. Run /aiagentminder:brief first to create your project plan."
Determine the Revision Type
The user's input will fall into one or more of these categories. Identify which apply and handle each:
A) Research Findings
The user has done research (competitor analysis, technical spike, user feedback, a document with recommendations) and wants the results folded into the plan.
How to handle:
- Read any document or input the user provides.
- Identify which findings affect the roadmap: new features, changed features, dropped features, new technical constraints, new decisions.
- For each actionable finding, apply the appropriate action below (B, C, D, or E).
- Summarize what changed and what was left as-is (not every research finding requires a plan change).
B) New Requirement
The user wants to add a feature or requirement that isn't in the plan.
How to handle:
- Determine the right phase placement — ask if unclear: "This sounds like it belongs in Phase [N]. Does that match your thinking, or should it go elsewhere?"
- Add the feature to the appropriate phase in
docs/strategy-roadmap.mdwith acceptance criteria (match the existing format). - If the feature displaces something or changes scope significantly, note what shifted.
- Log the addition in
DECISIONS.md: what was added, why, and what phase it targets.
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 · 146 lines · 15 tokens per session scan A 31de55a55bc6
revise is a skill published in the GitHub repository lwalden/AIAgentMinder (4 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,403 once invoked, about $0.0001 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
cn-check
Install and run the Continue CLI (cn) to execute AI agent checks on local code changes. Use when asked to "run checks", "lint with AI", "review my changes with cn", or set up Continue CI locally.
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
gr-readme
🇺🇸 GitHub README Writing System — Craft a README that converts visitors to stars in <3 seconds. Proven structure from AFFiNE's 0→60K star journey: tagline engineering, first-screen law, section-by-section copywriting guide, Claude Code integration section, anti-patterns, and a pre-publish checklist. Use when you…
joycraft-new-feature
Guided feature development — interview the user, produce a Feature Brief, then decompose into atomic specs.
joycraft-research
Invoked by design/decompose or the human directly — produce objective codebase research by isolating question generation from fact-gathering.
joycraft-collaborative-setup
Set up Joycraft for a team — scaffold per-area folders, owner conventions, and a team-facing CONTRIBUTING doc. Run once when adopting Joycraft on a multi-dev project.