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/zts0hg/codexspec/review-tasksgit clone --depth 1 https://github.com/Zts0hg/codexspecWrote 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/zts0hg/codexspec/review-tasks)<a href="https://agentmods.dev/commands/zts0hg/codexspec/review-tasks"><img src="https://agentmods.dev/badge/commands/zts0hg/codexspec/review-tasks.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 | $0.00017 | $0.01037 |
| Opus 5 | $0.00009 | $0.00518 |
| Sonnet 5 | $0.00003 | $0.00207 |
| Haiku 4.5 | $0.00002 | $0.00104 |
Grade A, and why
review-tasks 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasks Reviewer
Language Preference
Read .codexspec/config.yml. Two independent language controls apply (each falls back to language.output, then English):
- Interaction language (
language.interaction): language for all conversation with the user — questions, explanations, status messages, andcodexspecCLI terminal output. - Document language (
language.document): language for generated artifact files (requirements/spec/plan/tasks).
Converse in the interaction language and author artifacts in the document language. Apply the project's translation standard to both: translate by meaning (not word-for-word), keep English for terms with no good native equivalent, and write as if originally in that language.
User Input
$ARGUMENTS
Review Authority
Resolve by explicit path, then current branch; never silently select the latest feature.
Read requirements.md, spec.md, design.md, plan.md, tasks.md, the constitution, and relevant repository paths.
If requirements.md is absent, use legacy spec-only mode and disclose that original-discussion fidelity cannot be verified. A legacy feature may also have no design.md; when it is absent, proceed without the design link.
Authority order:
- Confirmed requirements
- Specification
- Constitution and verified repository facts
design.md- Approved plan
- Task list
- Applicable best practices
Review Passes
1. Fidelity and Coverage
- Map plan deliverables and
REQ/NFRitems to tasks. - Verify every task includes
Covers:and a plan reference, or is explicitly justified implementation support. - Detect omitted deliverables, unauthorized scope, redesign hidden inside tasks, and tasks based on superseded or open requirements.
2. Executability and Internal Quality
Report only evidence-backed defects:
- A task lacks a verifiable outcome
- Required paths or dependencies are wrong or impossible
- A dependency is circular or a dependent is ordered first
- Verification is insufficient for an actual requirement or repository quality gate
- Task boundaries make the result impossible to implement or validate
- A parallel marker is unsafe because declared work overlaps or depends on unfinished output
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 · 137 lines · 17 tokens per session scan A d795c3e3151d
review-tasks is a command published in the GitHub repository Zts0hg/codexspec (5 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 1,037 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 commands, from other repositories
review-agentready
AgentReady-specific code review with attribute mapping and score impact analysis.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit.clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.