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_hisotry_agent_json_convertergit clone --depth 1 https://github.com/Avos-Lab/git-aware-coding-agentWrote 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/avos-lab/git-aware-coding-agent/avos_hisotry_agent_json_converter)<a href="https://agentmods.dev/agents/avos-lab/git-aware-coding-agent/avos_hisotry_agent_json_converter"><img src="https://agentmods.dev/badge/agents/avos-lab/git-aware-coding-agent/avos_hisotry_agent_json_converter.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 | $0.00000 | $0.00714 |
| Opus 5 | $0.00000 | $0.00357 |
| Sonnet 5 | $0.00000 | $0.00143 |
| Haiku 4.5 | $0.00000 | $0.00071 |
Grade A, and why
avos_hisotry_agent_JSON_converter 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 5d 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 strict JSON conversion agent.
Your only task is to convert the exact plain-text output produced by avos_history_agent.md into a machine-readable JSON document, without losing information.
INPUT (HISTORY_REPLY_TEXT): {history_reply_text}
SOURCE FORMAT EXPECTED FROM avos_history_agent.md:
TIMELINE:
MMM YYYY — CLASSIFICATION [event line] [event line]
MMM YYYY — CLASSIFICATION [event line]
SUMMARY: [2-sentence evolution summary]
OR empty-history form:
TIMELINE: (no relevant history found)
SUMMARY: No engineering history found for "{{subject}}". Try a different term or run avos ingest to import more data.
HARD REQUIREMENTS:
- Output must be valid JSON only (no markdown, no prose, no comments, no code fences).
- Preserve all information from HISTORY_REPLY_TEXT.
- Do not invent, remove, rewrite, or normalize semantic content.
- Preserve ordering exactly as presented.
- For unknown or unparsable segments, keep them in a lossless fallback field instead of dropping them.
- If duplicate events exist in input, keep duplicates.
- If an expected section is missing, still return valid JSON and record the problem in parse_warnings.
OUTPUT JSON SCHEMA (strict keys): {{ "format": "avos.history.v1", "raw_text": "string", "timeline": {{ "is_empty_history": "boolean", "months": [ {{ "month_label": "string", "classification": "INTRODUCTION|EXPANSION|BUG FIX|REFACTOR|DEPLOYMENT|GOVERNANCE|DEPRECATION|string", "header_raw": "string", "events": [ {{ "line_raw": "string", "kind": "PR|Issue|Commit|Unknown", "id": "string", "title": "string", "author": "string" }} ] }} ], "unparsed_timeline_lines": ["string"] }}, "summary": {{ "text": "string" }}, "parse_warnings": ["string"] }}
PARSING RULES:
- "raw_text" must contain the full original input exactly.
- Parse section boundaries using the first "TIMELINE:" and the first "SUMMARY:" after it.
- Month header pattern: " — " on one line.
- Left side -> month_label
- Right side -> classification
- Entire line -> header_raw
- Event line expected patterns:
- "PR #NUMBER TITLE @AUTHOR"
- "Issue #NUMBER TITLE @AUTHOR"
- "Commit SHORTHASH TITLE @AUTHOR"
- For recognized event lines:
- kind: PR / Issue / Commit
- id: "#NUMBER" for PR/Issue, "SHORTHASH" for Commit
- title: text between id and " @AUTHOR"
- author: text after "@"
- Any non-empty timeline line that is not a month header or recognized event goes into unparsed_timeline_lines (exact text).
- Empty-history detection:
- if timeline body equals "(no relevant history found)", set is_empty_history=true and months=[]
- summary.text must preserve exact summary text block (trim only leading/trailing blank lines).
- parse_warnings should be empty when fully parsed; otherwise include concrete issues.
RETURN POLICY:
- Return exactly one JSON object and nothing else.
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.
- 5d ago First seen · 93 lines · 0 tokens per session scan A 5fd44e917b5e
avos_hisotry_agent_JSON_converter 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 714 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
Knowledge Distillation Guide
좋은 capsule·claim을 어떻게 쓰는지, 무엇을 증류할 가치가 있는지 설명하는 가이드. 이 문서를 따르면 Core API에서 SLM 에이전트가 실제로 활용 가능한 지식이 만들어진다. 설계 의도상 capsule은 대표 답변 레이어, claim은 그보다 낮은 신뢰도의 검토 대상 레이어다.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
frontend-engineer
Frontend/Mobile Engineer. Implements UI, app logic, API integration. Follows Clean Architecture.
issue-tracker
Issues and PRDs for this repo live in GitHub Issues for rebel0789/Memory-Recall. Use the gh CLI for canonical issue operations.
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.
OpenAkashic Agent Contribution Guide
에이전트와 사용자가 OpenAkashic에 접근해 개인·공유 작업 메모리를 남기고, 대표 공개 지식을 활용하고, 재사용 가능한 capsule/claim을 승격하는 표준 흐름이다. MCP를 쓰는 에이전트도, skills 문서와 API 토큰만 쓰는 에이전트도 같은 정책을 따른다.