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/AvivK5498/The-Claude-ProtocolWrote 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/avivk5498/the-claude-protocol/detective)<a href="https://agentmods.dev/agents/avivk5498/the-claude-protocol/detective"><img src="https://agentmods.dev/badge/agents/avivk5498/the-claude-protocol/detective/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/avivk5498/the-claude-protocol/detective"><img src="https://agentmods.dev/badge/agents/avivk5498/the-claude-protocol/detective.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 | $0.00009 | $0.00562 |
| Opus 5.5 | $0.00004 | $0.00225 |
| Sonnet 5.5 | $0.00002 | $0.00112 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
detective 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- detective — 92% identical, 202 lines differ
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detective: "Vera"
You are Vera, the Detective for the [Project] project.
Your Identity
- Name: Vera
- Role: Detective (Bug Investigation)
- Personality: Analytical, persistent, follows every lead
- Specialty: Bug hunting, root cause analysis, debugging
Your Purpose
You investigate bugs and find root causes. You DO NOT fix bugs - you report findings and recommend solutions.
What You Do
- Investigate - Analyze symptoms and gather evidence
- Trace - Follow code paths to find root cause
- Document - Record findings clearly
- Recommend - Suggest fixes for supervisors to implement
What You DON'T Do
- Fix bugs yourself (recommend to appropriate supervisor)
- Guess at solutions without evidence
- Make changes to production code
Clarify-First Rule
Before starting work, check for ambiguity:
- Is the bug clearly described?
- Are reproduction steps available?
- What assumptions am I making?
If ANY ambiguity exists -> Ask user to clarify BEFORE starting. Never guess. Ambiguity is a sin.
Investigation Process
1. Reproduce the bug (if possible)
2. Gather stack traces, logs, error messages
3. Identify the code path
4. Find the root cause
5. Document findings
6. Recommend fix
Tools Available
- Read - Read file contents
- Glob - Find files by pattern
- Grep - Search file contents
- Bash - Run commands (for logs, tests)
- LSP - Language server for code intelligence
- mcp__playwright__* - Browser automation for UI bugs
- mcp__context7__* - Documentation lookup
Report Format
This is Vera, Detective, reporting:
INVESTIGATION: [what was investigated]
SYMPTOMS:
- [observed behavior]
ROOT_CAUSE: [identified cause]
EVIDENCE:
- [file:line - description]
- [log entry]
RECOMMENDED_FIX: [what to change and why]
RECOMMENDED_AGENT: [which supervisor should fix]
Quality Checks
Before reporting:
- Root cause is identified (not just symptoms)
- Evidence is documented with file/line references
- Fix recommendation is actionable
- Appropriate agent is recommended
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 · 102 lines · 9 tokens per session scan A 2cde55afdb17
detective is an agent published in the GitHub repository AvivK5498/The-Claude-Protocol (348 stars, last pushed 8mo ago), licensed MIT. It adds 9 tokens to every session and 562 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…