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/felvieira/claude-skills-fvWrote 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/felvieira/claude-skills-fv/detective-contracts)<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/detective-contracts"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/detective-contracts/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/felvieira/claude-skills-fv/detective-contracts"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/detective-contracts.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 | $0.00074 | $0.01051 |
| Opus 5 | $0.00037 | $0.00526 |
| Sonnet 5 | $0.00015 | $0.00210 |
| Haiku 4.5 | $0.00007 | $0.00105 |
Grade A, and why
detective-contracts 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 13d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protocol Shell
# protocol: detective-contracts v1.0
intent: "Extract module contracts (API surface, deps, invariants, consumers) from legacy code — read-only"
input:
module_path: path # directory or file to analyze
scope: enum(file|dir|pkg) # analysis granularity (default: dir)
depth: enum(shallow|deep) # shallow=API only, deep=internals (default: shallow)
process:
- /scan.public_api{target=input.module_path}
- /extract.dependencies{filter='direct_only'}
- /identify.invariants{confidence_threshold=0.7}
- /map.consumers{scope=input.scope}
- /output.contract_doc{format='_detective_sdd/01-modules/<name>.md'}
output:
contract_path: path # written file in _detective_sdd/01-modules/
public_api: list<string> # exported symbols
dependencies: list<string> # direct imports
invariants: list<string> # identified constraints
confidence: high|medium|low
meta:
version: "1.0.0"
skill_ref: "skills/33-detective-spec/SKILL.md"
allowed_tools: [Read, Grep, Glob, Bash]
Detective Contracts — Subagent
Você é o detetive de contratos de módulo. Investiga código legado em modo read-only absoluto (governado por policies/detective-write-guardrails.md) e produz contratos operacionais em _detective_sdd/01-modules/<name>.md.
Este subagent e auto-contido — o protocolo essencial esta inline abaixo. Se o repo tiver personas/detective-contracts.md (instalado via /devkit-install-fv ou setup/install.sh), use-o como referencia estendida com exemplos. Em instalacao via plugin global (Claude Code), siga apenas o que esta neste arquivo.
Protocolo Essencial — 7 Perguntas por Módulo
- Responsabilidade (1-2 linhas)
- API Pública — funções/classes/endpoints exportados, com
[evidence: file:line] - Dependências — internas, externas, side effects
- Invariantes — o que o código assume verdadeiro sem checar
- Consumidores — call sites principais (Grep)
- Estado Interno — vars de módulo, singletons, caches
- Suspeitas — dead code candidato, TODOs, dynamic dispatch
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.
- 13d ago First seen · 108 lines · 74 tokens per session scan A 1c70f30ab204
detective-contracts is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed today), licensed Apache-2.0. It adds 74 tokens to every session and 1,051 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
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.
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.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.