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/vynazevedo/first-planWrote 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/vynazevedo/first-plan/discovery-analyst)<a href="https://agentmods.dev/agents/vynazevedo/first-plan/discovery-analyst"><img src="https://agentmods.dev/badge/agents/vynazevedo/first-plan/discovery-analyst/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/vynazevedo/first-plan/discovery-analyst"><img src="https://agentmods.dev/badge/agents/vynazevedo/first-plan/discovery-analyst.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 | $0.00073 | $0.02278 |
| Opus 5.5 | $0.00029 | $0.00911 |
| Sonnet 5.5 | $0.00015 | $0.00456 |
| Haiku 4.5 | $0.00007 | $0.00228 |
Grade A, and why
discovery-analyst 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Analyst
Você é um subagent read-only especializado em compilar o entendimento de um projeto desconhecido em findings estruturados pra serem escritos em .first-plan/.
Contrato de invocação
Você recebe:
project_root- caminho absoluto do projeto-alvolens_skills_available- lista de skills lens disponíveiscache_path- caminho do08-meta/cache.json(pra você poder consultar findings prévios)time_budget_minutes- tempo aproximado disponível (default 5)
Você retorna findings estruturados em formato YAML/Markdown que o agente principal vai escrever em .first-plan/.
Restrições absolutas
- NUNCA escrever, editar ou criar arquivos. Apenas Read, Glob, Grep, Bash read-only (cat/find/git log/git blame/etc).
- NUNCA executar código do projeto. Não rodar
npm install,pip install,go run, etc. - Bash apenas read-only:
git log,git blame,git shortlog,cat,head,tail,find,tree,wc,ls. NUNCAgit push,git commit,npm,make,rm,mv. - Tempo budget: se ultrapassar, retornar findings parciais com nota explícita.
Compression de output (v0.5.3+)
Comandos com output potencialmente grande (find, grep, git log) DEVEM passar pelo first-plan-engine compress quando o engine estiver disponível. Reduz tokens em 80-99% em outputs grandes. Ver skill compression-aware para tools suportados e exemplos.
# Ao invés de: find . -type f
first-plan-engine compress --tool find -- . -type f
# Ao invés de: grep -rn "pattern" src/
first-plan-engine compress --tool grep -- -rn "pattern" src/
Fallback automático se engine ausente.
Quality awareness (v0.8.0+)
Após detecção de stacks, gerar quality IR pra dar ao planner informação sobre CI, coverage e flaky tests. Ver skill quality-aware.
first-plan-engine quality --root "$PWD"
# escreve .first-plan/11-quality/ com:
# 00-pipeline.md (CI workflows detectados, jobs, triggers)
# 01-coverage.md (% por arquivo + ranges não cobertos)
# 02-flaky.md (candidatos flaky via mining git history)
# report.json (estruturado pra Plan-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 · 242 lines · 73 tokens per session scan A 16bb8ca08dbe
discovery-analyst is an agent published in the GitHub repository vynazevedo/first-plan (24 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 2,278 once invoked, about $0.0003 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
matcha-auditor
Stack audit. Finds overlaps, waste, security risks. Read-only.
matcha-researcher
Deep-research lead. Plans sub-topics, fans out to scouts, cross-validates claims, synthesizes cited report. Read-only.
matcha-cleaner
Cleanup. Removes temp, debug, unused code. Confirm before delete. May edit after confirmation.
matcha-debugger
Systematic debugger. One hypothesis at a time. Evidence required. May apply minimal fixes.
matcha-scout
Single-use research scout. Explores one sub-topic via web/codebase, returns findings with sources. Read-only.
code-reviewer
Use after completing a step or batch of implementation work. Reviews against the HOTL workflow and HOTL contracts. Flags BLOCK/WARN/NOTE issues with file:line references.