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 skills/matrixfounder/agentic-development/plan-review-checklistnpx skills add MatrixFounder/Agentic-development --skill plan-review-checklistgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWrote 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/matrixfounder/agentic-development/plan-review-checklist)<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/plan-review-checklist"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/plan-review-checklist.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 | $0.00012 | $0.01263 |
| Opus 5 | $0.00006 | $0.00632 |
| Sonnet 5 | $0.00002 | $0.00253 |
| Haiku 4.5 | $0.00001 | $0.00126 |
Grade A, and why
plan-review-checklist 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Review Checklist
1. Use Case Coverage
- Total Coverage: Every Use Case mapped to >= 1 Task?
- Traceability: Coverage table exists?
2. Structure & Formalism
- Stub-First: Every component has specific "Stub" and "Impl" phases/tasks?
- Dependencies: Task order respects dependencies?
- Phasing: Clear stages (Structure -> Logic -> Test)?
3. Task Descriptions
-
Existence: File exists for every task in
plan.md? -
Naming: Matches
task-{ID}-{SubID}-{slug}.md? -
Sections: Contains Goal, Changes, Test Cases, Acceptance Criteria?
-
Depth: Specific file paths and method signatures? (Without coding).
-
Strict Mode: Usage of
tdd-strictspecified for critical components/bugs?
4. Register (documentation-standards §5.5)
- Scan attached:
scan_register.py docs/PLAN.md docs/tasks/task-<ID>-*.md --sections --terms docs/ARCHITECTURE.mdwas run over every task file this plan produced, not a sample;DETECTORSshows none dead.<ID>is the Task ID fromdocs/TASK.mdsection 0. Task files carrying an earlier ID are the archive (skill-archive-taskmoves rotated documents into the same directory) and are out of this review's scope. - Warns resolved: zero
warn, or each survivor carries a written reason. - Reading pass covered: every section of every task file appears in the worklist and was read for rules 3, 4 and 6.
5. References (documentation-standards §4.1)
- Resolver run:
python3 .agent/skills/documentation-standards/scripts/check_positional_refs.py --all docs/PLAN.md docs/tasks/task-<ID>-*.mdwas run, and itspath:linecoverage line is quoted in the review — not asserted to have been produced. A checklist cannot prove a command ran; pasted output can. - Verdicts resolved: zero
REFERENT_ABSENTandREFERENT_AMBIGUOUS, or each survivor carries a written reason.REFERENT_MOVEDis repaired by re-running with--fix, never argued about — the number is derived from the referent, so no judgement is involved. - A coordinate carrying no referent is not a defect. It is reported as not examined and is NOT required to gain one. This review never demands a migration: most corpora carry no referents at all, and adoption is the project's decision, not the reviewer's.
- Cross-repository coordinates pinned: a path outside this repository resolves to nothing
and reports
UNRESOLVABLE. It carries@<rev>naming the revision measured, which is the form §4.1 already licenses for a claim about another state.
Scope caveat, the same one this checklist's Script Contract states for the register scan.
docs/tasks/is also the permanent archive sink, so the bare globdocs/tasks/*.mdwould put every task ever written under this section. Substitute the current Task ID for<ID>.
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.
- 4d ago First seen · 86 lines · 12 tokens per session scan A e11e57cb72bc
plan-review-checklist is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 12 tokens to every session and 1,263 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
Learn what defines effective BDD scenarios
Interactive guidance on writing complete, effective BDD scenarios for story-flow.
add-tests
Generates tests for existing code. Analyzes the target function, method, or class to identify the happy path, error cases, and edge cases, then writes test cases following the project's testing framework and naming conventions. Invoked when the user asks to add tests, write tests, cover code, or increase coverage.
tdd-implementation
Use when implementing any code change for a task – new behavior, a bugfix, or a revision after review – before writing the production code. Defines the failing-test-first cycle, public-seam testing, vertical slices, scaffold and infra handling, and counters to common excuses for tests-after-code.
test-writer
Writes tests that fail before a fix and pass after it.
test-generation
Generate and run unit/integration tests TDD-style across Python, Node, and .NET. Use when adding tests to untested code, implementing a feature test-first, or finding coverage gaps.
argent-tv-interact
Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…