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 skills add Tirefly/agent-harness-template --skill harness-retrogit clone --depth 1 https://github.com/Tirefly/agent-harness-templateWrote 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/skills/tirefly/agent-harness-template/harness-retro)<a href="https://agentmods.dev/skills/tirefly/agent-harness-template/harness-retro"><img src="https://agentmods.dev/badge/skills/tirefly/agent-harness-template/harness-retro/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/skills/tirefly/agent-harness-template/harness-retro"><img src="https://agentmods.dev/badge/skills/tirefly/agent-harness-template/harness-retro.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 | $0.00101 | $0.01089 |
| Opus 5 | $0.00051 | $0.00544 |
| Sonnet 5 | $0.00020 | $0.00218 |
| Haiku 4.5 | $0.00010 | $0.00109 |
Grade A, and why
harness-retro 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 9d 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
Harness Retro：任务结束的经验沉淀
触发条件（满足其一即提议）
- 设计/分析任务产出交付物
- 失败后重试成功
- 用户纠正了 agent 的判断
- 做出不可逆或高影响的决策
- 长任务会话将尽且存在未关闭 checkpoint（→ 产出新 checkpoint）
触发评估由 AGENTS.md「回答后 TAH 判定」在每次回答结束时强制执行：命中任一条件即加载本技能并主动提议，无需用户显式声明"执行 TAH 检查"。提议后等待用户决定；草稿与入库仍走人工门控，绝不自动写卡。
跳过条件
纯查询、格式微调、单文件小改动。跳过时不必说明。 同一会话刚执行过 retro 且此后无新触发 → 不重复提议。
流程（六步，不得跳步）
1. 会话回顾
本次任务：尝试了什么 → 什么失败了 → 用户纠正了什么 → 用户应用了什么判断标准。
2. effectiveness 回写
本次注入的记忆哪些 helpful / misleading / unused？逐张写回对应卡片 effectiveness 字段（追加一条 {date, task, verdict, note}）。 连续 ≥2 次 misleading 的卡：主动向用户提议 supersede。
3. 起草候选卡
每任务最多 3 张，宁缺毋滥。按四类归位（judgment/lessons/decisions/preferences），用 ../harness-router/templates/memory-card.md 模板。
- keywords 必须含同义词（中英），保证字面检索可命中语义近邻
- 与现有卡冲突 → 起草 supersede 关系（旧卡 status 改 superseded-by 的操作在采纳后的一条龙中执行，起草期不动旧卡），不并列共存
- checkpoint 卡用
templates/checkpoint-card.md，一律写入~/.agents/memory/decisions/（写入其他目录会被检索索引静默跳过）
4. 人工门控
按 references/gate-workflow.md 执行：逐张呈现草稿，用户 [采纳 / 修改后采纳 / 丢弃]；用户可口述补充。未过门控的草稿一律丢弃。
5. 入库一条龙（仅采纳的卡）
写卡片文件 → 更新 ~/.agents/memory/INDEX.md 对应表（追加一行）→
python ~/.agents/skills/harness-router/scripts/retrieve.py --rebuild →
git -C ~/.agents add memory && git -C ~/.agents commit -m "memory: <卡片标题>"（memory 由外层仓库跟踪，add 范围限定 memory，不裹挟其他改动；PowerShell 参数位 ~ 不展开时，先把 ~ 替换为 $env:USERPROFILE 得到本机绝对路径再执行）
【裁决追加】Python 探测顺序：python → uv run python → 本机已知绝对路径。本机兜底路径在对应技能文件的本机裁决注释中维护（跨机部署时替换为新机器的实际路径）。
四步必须连续完成，中断则回滚已完成步骤（删卡/还原 INDEX）后重来。
入库前顺手 grep 校验：INDEX 中该 id 唯一。
6. 无卡收场
确实没有值得沉淀的 → 明确说"本次无沉淀"并结束。这是纪律，不是失败。
若步骤 2 已回写 effectiveness，单独提交该改动（git -C ~/.agents add memory && git -C ~/.agents commit -m "memory: effectiveness 回写"；~ 参数位处理同上）。
关闭 checkpoint
任务完成时：将相关 task-open 卡 status 改为 active，正文追加"## 收束"一节写最终结论，走门控后提交。
同步更新 ~/.agents/memory/INDEX.md 对应行的 status 列（避免幻影断点：router 靠 grep INDEX 找 task-open），并执行 retrieve.py --rebuild。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 54 lines · 101 tokens per session scan A 3e47170b3445
harness-retro is a skill published in the GitHub repository Tirefly/agent-harness-template (2 stars, last pushed 14d ago), licensed MIT. It adds 101 tokens to every session and 1,089 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.