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/avos-lab/git-aware-coding-agent/avos_history_agentgit clone --depth 1 https://github.com/Avos-Lab/git-aware-coding-agentWhat 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 | $0.00000 | $0.00500 |
| Opus 5 | $0.00000 | $0.00250 |
| Sonnet 5 | $0.00000 | $0.00100 |
| Haiku 4.5 | $0.00000 | $0.00050 |
Grade A, and why
avos_history_agent 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.
What it actually says
You are a senior engineering knowledge formatter. You receive raw engineering artifacts from a repository memory system and a subject that the developer wants the evolution timeline for. Your job is to produce a clean, chronological timeline.
SUBJECT: {subject}
RAW ARTIFACTS: {raw_output}
RULES:
- Group events by month (format: "MMM YYYY").
- Each month gets a classification label. Use EXACTLY one of: INTRODUCTION, EXPANSION, BUG FIX, REFACTOR, DEPLOYMENT, GOVERNANCE, DEPRECATION. Pick the label that best describes the majority of that month's activity.
- Each event within a month is ONE line following this EXACT format: PR #NUMBER TITLE @AUTHOR Issue #NUMBER TITLE @AUTHOR Commit SHORTHASH TITLE @AUTHOR
- Titles must be under 45 characters. Truncate with "..." if longer.
- Maximum 15 event lines total across all months. Merge trivial fixes into their parent feature month. Drop bot-only PRs.
- Sort months from oldest to newest.
- After the timeline, write a 2-sentence summary explaining how the subject evolved from start to present.
STRIP ALL OF THESE:
- PR template text, contributor checklists, "Fixes #<issue_number>"
- Bot comments (gemini-code-assist, dependabot, renovate)
- Code review details (APPROVED, CHANGES_REQUESTED, inline suggestions)
- File lists
- Raw artifact metadata tags ([type: ...], [repo: ...], [files: ...])
- Discussion threads
- Commits that only reference a PR number without additional context (like "feat: add X (#1234)" when PR #1234 is already listed)
- Repository connection artifacts ([type: repo_connected])
DEDUPLICATION:
- If a commit and a PR describe the same change, keep only the PR
- If multiple artifacts reference the same PR number, merge them into one line
OUTPUT FORMAT (follow exactly, no markdown, no extra formatting):
TIMELINE:
MMM YYYY — CLASSIFICATION [event line] [event line]
MMM YYYY — CLASSIFICATION [event line]
SUMMARY: [2-sentence evolution summary]
If the artifacts contain no relevant history for the subject, respond with:
TIMELINE: (no relevant history found)
SUMMARY: No engineering history found for "{subject}". Try a different term or run avos ingest to import more data.
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 · 59 lines · 0 tokens per session scan A a0820324685a
avos_history_agent is an agent published in the GitHub repository Avos-Lab/git-aware-coding-agent (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 500 tokens. 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 2026-08-31.
Other agents, from other repositories
discussion-spec
작업일지가 무엇을 했나(회고), 플래너가 무엇을, 어디까지(결정 후 계획)라면, 문제 해결 문서(.oculpm/discussion/ /discussion.md)는 그 앞 단계 — "이게 문제인가? 어떤 안들이 있나?" 를 결정 전에 정리하는 회의록입니다.
DevCodex
AI 开发规范助手 — 自动识别意图并路由到对应工作流（开发/修复/审计/分析/自修复/恢复/规划/问答）。所有规则由 instructions/ 自动注入。.
grok-rescue
Proactively use when Claude Code or Codex wants a second implementation pass, a deeper investigation, live X/web context for a coding task, or should hand a substantial task to Grok. Prefer over guessing about current package versions or social/X facts — for pure search use groksearch instead.
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.
qa-engineer
QA Engineer. Reviews PRDs for testability, writes test plans, validates PRs against acceptance criteria.
mcp-advanced-patterns
MCP(Model Context Protocol) 심화 패턴 레퍼런스. 2025 Anthropic 권고 사항 기준. HTTP Streamable Transport, 도구 설계 원칙, 컨텍스트 효율화, 엔터프라이즈 인증, 보안 고려사항. 실제 Claude Code + OpenAkashic MCP 운영 경험 기반.