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/9j/rapidspec/reviewgit clone --depth 1 https://github.com/9j/RapidSpecWhat 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 | $0.03532 |
| Opus 5 | $0.00009 | $0.01766 |
| Sonnet 5 | $0.00003 | $0.00706 |
| Haiku 4.5 | $0.00002 | $0.00353 |
Grade A, and why
RapidSpec: Review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 502 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review RapidSpec Implementation
<command_purpose> Perform exhaustive code reviews using multi-agent analysis for deep quality assurance. Reviews validate implementation against spec, ensuring security, performance, and maintainability. </command_purpose>
Introduction
Senior Code Review Architect with expertise in security, performance, architecture, and quality assurance
Review Target
<review_target> #$ARGUMENTS </review_target>
Main Tasks
1. Read Spec and Implementation (ALWAYS FIRST)
<critical_requirement> MUST read spec files BEFORE running agents. No exceptions. Agents need context to provide relevant feedback. </critical_requirement>
Immediate Actions:
- Read
rapidspec/changes/<change-id>/proposal.md- What was planned - Read
rapidspec/changes/<change-id>/tasks.md- What tasks were defined - Run
git diff- What was actually implemented - Compare implementation against proposed changes
2. Detect Project Type
<project_type_detection>
Check for these indicators:
Next.js Project:
package.jsonwith"next"dependencyapp/orpages/directorynext.config.js.tsxor.tsfiles
Supabase Project:
supabase/directorysupabase/migrations/folder.sqlmigration files- Supabase client imports
TypeScript Project:
tsconfig.json.tsor.tsxfiles
Based on detection, include project-specific reviewers in parallel execution.
</project_type_detection>
3. Selective Agent Review
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.
- yesterday First seen · 502 lines · 0 tokens per session scan A c2e0523d8efb
RapidSpec: Review is a command published in the GitHub repository 9j/RapidSpec (5 stars, last pushed 9mo ago), licensed MIT. It adds 17 tokens to every session and 3,532 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
checklist
Generate a custom checklist for the current feature based on user requirements.
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.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.