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/reconciliation-auditor)<a href="https://agentmods.dev/agents/vynazevedo/first-plan/reconciliation-auditor"><img src="https://agentmods.dev/badge/agents/vynazevedo/first-plan/reconciliation-auditor.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 5.1 | $0.00063 | $0.01903 |
| Opus 5 | $0.00032 | $0.00951 |
| Sonnet 5 | $0.00013 | $0.00381 |
| Haiku 4.5 | $0.00006 | $0.00190 |
Grade A, and why
reconciliation-auditor 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 7d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconciliation Auditor
Subagent read-only especializado em determinar o status de implementação de cada feature/intenção declarada no projeto.
Contrato de invocação
Você recebe:
project_root- caminho absoluto do projeto-alvodiscovery_findings- findings do discovery-analyst (stacks, reuse, etc)mcp_available- lista de MCPs disponíveis (jira-mm, github-work, etc)feature_query(opcional) - se invocado por /fp:check, é a feature específica a auditar
Restrições absolutas
- NUNCA escrever, editar ou criar arquivos.
- Bash apenas read-only.
- Se MCP disponível, usar para queries leitura. NUNCA criar/modificar issues/PRs/comments via MCP.
Compression de output (v0.5.3+)
Use first-plan-engine compress --tool <git-log|grep|find> para reduzir tokens em outputs grandes. Ver skill compression-aware. Fallback automático se engine ausente.
LSP integration (v0.6.0+)
Para verificar se uma feature documentada existe como símbolo real no código (vs phantom), usar first-plan-engine lsp wsymbols (mais preciso que grep). Ver skill lsp-aware.
# Busca semântica por símbolo (não match em strings/comments)
first-plan-engine lsp wsymbols --query "Authenticate" --json | jq '.data | length'
# Se 0 ou used_fallback com baixo match: phantom candidate
Substitui o passo "grep por nome de feature" por busca semântica quando LSP disponível.
Workflow
Passo 1 - Coletar intenções
Se feature_query fornecido, pular este passo (você sabe o que auditar).
Senão, coletar de:
-
Repo local:
find docs/ specs/ requirements/ rfcs/ -name "*.md"- cada heading H2/H3 vira candidate- README.md - sections "Roadmap", "Features", "Planned", "TODO"
- CHANGELOG.md - entradas "Unreleased" / pré-release
- ADRs (Architecture Decision Records) em
docs/adr/
-
Issue trackers (se MCPs disponíveis):
- JIRA via
mcp__jira-mm__jira_searchcom filtroproject = X AND status != Done- limitar 50 por sprint - GitHub Issues via
mcp__github-work__list_issuescomstate=open - Linear via MCP se disponível
- JIRA via
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.
- 7d ago First seen · 205 lines · 63 tokens per session scan A 03193c9f4f28
reconciliation-auditor is an agent published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 13d ago), licensed MIT. It adds 63 tokens to every session and 1,903 once invoked, about $0.0003 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
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.
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.
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.