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 agents/vynazevedo/first-plan/discovery-analystgit 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.svg" alt="Measured on agentmods" 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 | $0.00073 | $0.02278 |
| Opus 5 | $0.00036 | $0.01139 |
| Sonnet 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 4d 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.
- 4d 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 (23 stars, last pushed 10d ago), licensed MIT. It adds 73 tokens to every session and 2,278 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
release-captain
Drives a release end to end per RELEASING.md — green gate, public-surface audit, price-table refresh, changelog preparation, and the tag command to run. Stops before anything is pushed.
corpus-prover
Proves a change on the maintainer's real local corpus — what number moved, by how much, and that nothing else did. Use before calling any measurement change done. Never writes to the real store.
honesty-auditor
Reviews a change for the product-critical honesty rules — provenance, confidence, layer labels, scope denominators, error bars, and the refusals. Use on any change that adds, renames, or reshapes a number a user reads. Read-only.
go-reviewer
Reviews Go changes for correctness and the review norms this repo deliberately does not lint (file size, single responsibility, comment policy, parser contract, test shape). Use after any code change, before a release. Read-only.
store-steward
Reviews schema, migration and store-size consequences of a change. Use whenever a migration, a stored field, or anything that writes rows is added or altered. Read-mostly.
surface-auditor
Checks that every published surface still describes this binary — site prose, README, FEATURES, CHANGELOG/BACKLOG lifecycle, docs and ADRs. Use on any user-facing change and before every tag. Read-mostly.