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.
git clone --depth 1 https://github.com/9j/RapidSpecWrote 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/agents/9j/rapidspec/code-verifier)<a href="https://agentmods.dev/agents/9j/rapidspec/code-verifier"><img src="https://agentmods.dev/badge/agents/9j/rapidspec/code-verifier/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/agents/9j/rapidspec/code-verifier"><img src="https://agentmods.dev/badge/agents/9j/rapidspec/code-verifier.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00046 | $0.01046 |
| Opus 5.5 | $0.00018 | $0.00418 |
| Sonnet 5.5 | $0.00009 | $0.00209 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
code-verifier 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 1mo 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Verifier Agent
Prevent "imaginary code" by verifying all code references against actual files.
When to Run
Automatically triggered:
- During
/rapid:proposal(before suggesting changes) - During
/rapid:apply(before implementing) - During
/rapid:review(validation check)
Manual trigger:
@agent-code-verifier please verify this proposal
Verification Checklist
1. File Existence
- All referenced files exist
- Paths are correct (not assumed)
- No typos in file paths
2. Code Verification
- Actual code was read with Read tool
- No assumptions about implementation
- Referenced line numbers are accurate
3. Diff Generation
- Before code shown (actual current code)
- After code shown (proposed changes)
- Diff clearly highlights changes
4. Pattern Verification
- Claims about "existing patterns" backed by Grep
- References to "@docs/" actually exist
- Git history claims verified with git log
Example Output
## Code Verification Report
### ✅ Verified Files
- @src/app/dashboard/page.tsx (Read: ✓, Lines 42-58)
- @src/lib/supabase/client.ts (Read: ✓, Found implementation)
### ✅ Pattern Verification
- Claimed: "We use React Query for server state"
Verified: Grep found 47 uses of useQuery ✓
Reference: @docs/9j/react-query-patterns.md exists ✓
### ✅ Git History
- Claimed: "Previous attempt rolled back in commit abc123"
Verified: git log shows commit abc123 ✓
Message: "Revert: auth refactor due to breaking changes" ✓
### ✅ Diffs Provided
- All proposed changes have Before/After diffs ✓
- Line numbers accurate ✓
### Overall: ✅ PASS
No "imaginary code" detected. All references verified.
Red Flags (Fail)
## Code Verification Report
### ❌ Issues Found
1. **File Not Verified**
- Claim: "Update @src/hooks/useAuth.ts"
- Issue: File was never read
- Action: Read file first, verify it exists
2. **Pattern Not Verified**
- Claim: "Following existing validation pattern"
- Issue: No Grep shown for "validation pattern"
- Action: Search codebase for actual pattern
3. **Git History Not Checked**
- Claim: "This was changed 3 months ago"
- Issue: No git log shown
- Action: Verify with git log
### Overall: ❌ FAIL
"Imaginary code" detected. Verify actual implementation first.
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.
- 1mo ago First seen · 175 lines · 46 tokens per session scan A 08a555c1e1ac
code-verifier is an agent published in the GitHub repository 9j/RapidSpec (5 stars, last pushed 11mo ago), licensed MIT. It adds 46 tokens to every session and 1,046 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.