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 skills/vynazevedo/first-plan/git-intelligencenpx skills add vynazevedo/first-plan --skill git-intelligencegit clone --depth 1 https://github.com/vynazevedo/first-planWhat 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 | $0.00058 | $0.01536 |
| Opus 5 | $0.00029 | $0.00768 |
| Sonnet 5 | $0.00012 | $0.00307 |
| Haiku 4.5 | $0.00006 | $0.00154 |
Grade A, and why
first-plan-git-intelligence scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Intelligence
Extração de sinal do git que humanos veem mas IA tipicamente ignora.
Engine acceleration (v0.3.0+)
Para hashing de arquivos do cache (08-meta/cache.json), preferir o binário first-plan-engine se disponível:
# Detectar engine (igual co-change-analysis)
ENGINE=""
for c in "${CLAUDE_PLUGIN_ROOT}/engine/bin/first-plan-engine" "${HOME}/.local/bin/first-plan-engine" "$(command -v first-plan-engine 2>/dev/null)"; do
[ -x "$c" ] && ENGINE="$c" && break
done
if [ -n "$ENGINE" ]; then
# xxh3 paralelo via rayon - 10x mais rapido que sha256 + bash loop
find . -type f -not -path "./.git/*" -not -path "./node_modules/*" | \
"$ENGINE" hash --paths-from-stdin --output-json .first-plan/cache/files.json
fi
JSON schema first-plan-hash-v1 em 08-meta/cache.json (ou similar).
Compression de output (v0.5.3+)
Comandos git log, git status, git diff podem gerar muito output em repos grandes. Use first-plan-engine compress (ver skill compression-aware) para reduzir tokens em 30-80%:
# Ao invés de:
git log --oneline -n 100
# Use:
first-plan-engine compress --tool git-log --json -- -n 100
# retorna JSON com .output já comprimido
Compressão automática quando engine disponível, fallback graceful sem ele.
Pré-requisito (fallback)
Projeto deve ser git repo. Se nao for, todas as seções correlatas em .first-plan/01-topology/activity.md, 01-topology/ownership.md, 07-state/in-flight.md ficam vazias com nota explicativa.
test -d .git || echo "Not a git repo"
Activity heatmap
Top arquivos por commits recentes
git log --since="90 days ago" --name-only --pretty=format: \
| grep -v '^$' \
| sort | uniq -c | sort -rn \
| head -20
Output em .first-plan/01-topology/activity.md na seção "Top 20 arquivos".
Top pastas
git log --since="90 days ago" --name-only --pretty=format: \
| grep -v '^$' \
| xargs -I{} dirname {} \
| sort | uniq -c | sort -rn \
| head -20
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.
- 2d ago First seen · 204 lines · 58 tokens per session scan A 0badf65eb45b
first-plan-git-intelligence is a skill published in the GitHub repository vynazevedo/first-plan (23 stars, last pushed 8d ago), licensed MIT. It adds 58 tokens to every session and 1,536 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 skills, from other repositories
RecallMax
Enhances AI memory capabilities with long-context support.
agent-memory
Persistent memory system for AI coding agents. Use when you need to save facts about the user, store interaction preferences, log session events, or search previously saved memories. Triggers on remembering, saving context, recalling past decisions, or when the user says "remember this". Also use proactively when the…
snip
You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.
arch-check
架构与实现审查 —— 基于「概念建模 → 职责划分 → 机制/策略分离 → 因果与不变量 → 属性建模 → 模块化 → SOLID → GRASP → YAGNI」的全维度审查,带置信度门控与假阳性抑制(对抗"过度工程建议"这类 AI slop)。触发于:要求 review/审查架构、检查目录结构/依赖关系/职责划分、重构前评估、技术债盘点、判断是否过度设计,或问「这个设计合理吗 / 该怎么拆 / 有没有循环依赖 / 这个改动架构上 OK 吗」。一律按最高强度审查。用法:arch-check [范围] [--fix|--plan]。范围可为目录/文件/PR;缺省审当前分支相对基线的全部变更。.
e2e
Selects and runs the appropriate AgentsMesh end-to-end suite for Web, Desktop, MCP, or iOS, including worktree-specific environment setup and browser-level verification. Use when a change needs E2E coverage, a user asks to execute or diagnose an E2E test, or a cross-service workflow must be verified against the real…
gh-merge
Completes the AgentsMesh GitHub pull-request workflow: commits scoped changes, rebases on the authoritative GitHub branch, opens or reuses a PR, monitors required checks, fixes failures, and merges only after verification. Use when the user asks to merge, submit, or land repository changes.