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 rube-de/cc-skills --skill review-plangit clone --depth 1 https://github.com/rube-de/cc-skillsWrote 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/rube-de/cc-skills/review-plan)<a href="https://agentmods.dev/skills/rube-de/cc-skills/review-plan"><img src="https://agentmods.dev/badge/skills/rube-de/cc-skills/review-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/rube-de/cc-skills/review-plan"><img src="https://agentmods.dev/badge/skills/rube-de/cc-skills/review-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 | $0.00066 | $0.02111 |
| Opus 5 | $0.00033 | $0.01056 |
| Sonnet 5 | $0.00013 | $0.00422 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
review-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 11d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Plan — External Consultant Validation
External consultants + codebase verification catch plan flaws before execution begins.
Workflow
digraph review_plan {
rankdir=TB;
node [shape=box];
locate [label="Step 1: Locate Plan"];
verify [label="Step 2: Codebase Verification"];
launch [label="Step 3: Launch Consultants\n(gemini + codex in parallel)"];
synthesize [label="Step 4: Deduplicate & Synthesize"];
present [label="Step 5: Present Structured Output"];
decide [label="Step 6: User Decision"];
locate -> verify -> launch -> synthesize -> present -> decide;
decide -> execute [label="Ready to execute"];
decide -> revise [label="Needs revision"];
decide -> discuss [label="Needs discussion"];
execute [label="Offer execution handoff" shape=ellipse];
revise [label="List specific changes\nAsk: revise or proceed?" shape=ellipse];
discuss [label="Present trade-offs\nfor user decision" shape=ellipse];
}
Step 1: Locate Plan
Check these sources in order — use the first match:
- Explicit argument: If the user provided a file path, use it
- Conversation context: If a plan was written or pasted earlier in this conversation, use that content
- Plan directory discovery: From the repository root, search both plan directories and use the most recently modified
.mdfile:
Note: Run this from the repo root, not from the skill directory.ls -t .dev/cdt/plans/*.md docs/plans/*.md 2>/dev/null | head -1
If no plan is found, ask the user with AskUserQuestion.
Read the full plan content before proceeding.
Step 2: Codebase Verification
Verify every concrete claim in the plan against the actual codebase. Check ALL of:
| Claim Type | Verification Method | Failure = |
|---|---|---|
| File paths (modify/delete) | Glob for existence |
Critical — plan references nonexistent files |
| File paths (create) | Verify parent directory exists | Note — files being created are expected to be absent |
| Line numbers | Read the file, check lines match |
Warning — line numbers may have drifted |
| API signatures | Grep for function/method names, verify params |
Critical — API has changed |
| Import paths (relative only) | Glob for referenced module path, then Read to confirm expected export — skip package imports (react, lodash) and alias imports (@/lib/db) |
Critical — module doesn't exist or export is missing |
| Duplicate work | Grep for existing implementations |
Warning — feature may already exist |
| Test files | Glob for existing test files in same area |
Note — tests may already cover this |
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.
- 11d ago First seen · 237 lines · 66 tokens per session scan A 526a2792adeb
review-plan is a skill published in the GitHub repository rube-de/cc-skills (10 stars, last pushed 5d ago), licensed MIT. It adds 66 tokens to every session and 2,111 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
great_cto
Use when the CTO describes a feature, task, or project goal. Orchestrates the full SDLC pipeline automatically based on project type.
vertical-hr-recruiting
Domain-knowledge primer for the HR & recruiting vertical (ATS, onboarding, workforce scheduling, engagement). Applied by architect/pm during spec authoring so they aren't naive about hiring pipelines, the admitted offer→onboard data-carry gap, EEO/I-9 compliance, and shift-coverage rules. Stops the four products from…
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
opportunity-solution-tree
Build an Opportunity Solution Tree (OST) to structure product discovery — map a desired outcome to customer opportunities, possible solutions, and experiments. Based on Teresa Torres' Continuous Discovery Habits. Use when the team is unclear what to build next, when multiple opportunities compete, or before writing a…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
vertical-fintech-mobile
Domain-knowledge pack for money on a phone — wallets, payments, custody and signing, transaction lifecycle, KYC/AML gates, and offline reconciliation. The rules that separate a payments app from a CRUD app with a currency symbol: a balance is a claim about a server, an idempotency key must outlive the process that…