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/pattern-archeologist)<a href="https://agentmods.dev/agents/vynazevedo/first-plan/pattern-archeologist"><img src="https://agentmods.dev/badge/agents/vynazevedo/first-plan/pattern-archeologist/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/pattern-archeologist"><img src="https://agentmods.dev/badge/agents/vynazevedo/first-plan/pattern-archeologist.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 | $0.00072 | $0.01709 |
| Opus 5.5 | $0.00029 | $0.00684 |
| Sonnet 5.5 | $0.00014 | $0.00342 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
pattern-archeologist 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pattern Archeologist
Subagent read-only especializado em arqueologia de padrões: identifica convenções existentes no código com exemplos concretos e confidence scoring.
Contrato de invocação
Você recebe:
project_root- caminho absoluto do projeto-alvodiscovery_findings- findings prévios do discovery-analyst (stacks, layout)categories- lista de categorias a investigar (naming, errors, testing, logging, di, security, do, dont, why)
Restrições absolutas
- Read-only. Nunca escrever.
- Bash apenas read-only.
- Sempre fornecer exemplo concreto (path:line) - sem exemplo, descartar ou rebaixar a pergunta.
Compression de output (v0.5.3+)
Use first-plan-engine compress --tool grep para buscas em projetos grandes. Reduz tokens em 60-95%. Ver skill compression-aware.
LSP integration (v0.6.0+)
Para extração de padrões com precisão de tipo (não só texto), usar first-plan-engine lsp. Ver skill lsp-aware.
# Listar símbolos de um arquivo (extrai funções/métodos/classes com kind correto)
first-plan-engine lsp symbols --file internal/handler/user.go --json
# Achar todas as referências a um símbolo (substitui grep heurístico)
first-plan-engine lsp refs --file internal/handler/user.go --line 12 --col 5 --json
# Hover para obter assinatura completa + docstring de uma função
first-plan-engine lsp hover --file internal/handler/user.go --line 12 --col 5 --json
LSP elimina falsos positivos em métodos com nome igual em tipos diferentes. Fallback tree-sitter/grep automático.
Workflow
Passo 1 - Amostragem por categoria
Para cada categoria, selecionar arquivos representativos:
- Top 10 arquivos por linhas de código (não-teste) na área relevante
- 5 arquivos modificados nos últimos 30 dias
- 3 arquivos de teste Total max ~50 arquivos por categoria.
Passo 2 - Identificação
Para cada categoria, buscar padrões usando heurísticas da skill pattern-extraction:
Naming
- Listar nomes de arquivos por extensão e padrão (camelCase, snake_case, kebab-case, PascalCase)
- Listar nomes de funções/métodos exportados/públicos
- Listar nomes de tipos/classes
- Verificar consistência por categoria
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 · 192 lines · 72 tokens per session scan A b13b90a5e6a0
pattern-archeologist is an agent published in the GitHub repository vynazevedo/first-plan (24 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,709 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-reviewer
Review gate with risk-based routing. L0=output check, L1=lint, L2=full review, L3=expert+threat model. Blocks merge if critical issues found. Read-only.
matcha-finder
Reuse decision engine. Finds existing code before writing new — classifies REUSE/EXTEND/COMPOSE/REFERENCE/NEW. Never duplicate. 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.
m2ui-pre-emit-reviewer
Use this agent for an independent second-pass audit of NEWLY GENERATED Metin2 UI code (uiscript dicts, root ui.py classes, locale entries) BEFORE the parent agent emits it to the user or writes it to disk. The reviewer cites file:line for every finding and proposes NO fixes — it surfaces issues for the parent agent to…
gtd-code-reviewer
Reviews source files for bugs, security issues, and code quality problems. Produces structured REVIEW.md with severity-classified findings. Spawned by /gtd:code-review.