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 yibie/SPEC-AGENTS.md --skill learngit clone --depth 1 https://github.com/yibie/SPEC-AGENTS.mdWrote 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/yibie/spec-agents.md/learn)<a href="https://agentmods.dev/skills/yibie/spec-agents.md/learn"><img src="https://agentmods.dev/badge/skills/yibie/spec-agents.md/learn/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/yibie/spec-agents.md/learn"><img src="https://agentmods.dev/badge/skills/yibie/spec-agents.md/learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.01646 |
| Opus 5.5 | $0.00025 | $0.00658 |
| Sonnet 5.5 | $0.00013 | $0.00329 |
| Haiku 4.5 | $0.00006 | $0.00165 |
Grade A, and why
learn 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn
把运行结果变成可复用的知识，但不把每次试错都升级成长期规则。
记录证据
只记录会影响后续判断的增量，追加到 .spec-agents/state/EVIDENCE.md：
## <date> — <subject>
### Observation
### Interpretation
### Recommended next action
### Verification
### References
把观察、解释和建议分开；不要写会话流水账或重复 git diff。
在 .jj/ 项目中，Evidence 的 References 可以记录可复核的 JJ Change ID、
bookmark 和 jj diff/jj log 结果；不要把 JJ Change 当作语义 Change，也不要
要求远端发布才能完成本地 learn。Git-only 项目继续记录其现有 commit/branch
证据。
如果来源 Slice 有 evidence_ref：先为本次结果分配稳定 Evidence ID，追加
.spec-agents/state/EVIDENCE.md，验证写入成功后，再把同一个 ID 回写 Slice。不要在验证前
预填链接；learn 是唯一写入者。
判断知识类别与提升层级
- 只影响当前任务：留在 Slice 或 SPEC，不提升；短路径上不留任何记录。
- 可复用但尚未成为规则的事实、失败假设或验证结果：追加
.spec-agents/state/EVIDENCE.md。 - 项目稳定概念、身份、关系、生命周期或不变量：经
plan确认后更新项目.spec-agents/state/KERNEL.md；项目自己的词汇和权威边界更新CONTEXT.md；只有 SPEC-AGENTS 工作流自身的语义才更新.spec-agents/doctrine/docs/WORKFLOW.md。 Kernel 的写入内容必须等于该 SPEC 最近修订时声明的kernel_delta条目；每个提升 条目的 provenance（source:）都必须引用该 SPEC。 - 稳定接口、状态转换或 Action Contract：经
plan确认后更新docs/protocols/。 - 稳定的开发、评审、测试或协作约定：经
plan确认后更新docs/protocols/。 - 带前置条件、验证和恢复路径的重复操作：经
plan确认后更新docs/runbooks/。 - 有明确适用范围的失败教训或重复模式：经
plan确认后更新docs/lessons/；不要把 scoped lesson 直接写成全局不变量。 - 难以逆转、出乎预期且源于真实取舍的决定：创建
docs/adr/中的 ADR。 - 活跃 SPEC、阻塞项或下一步改变：更新
.spec-agents/state/STATUS.md。SPEC 完成时把它从.spec-agents/state/STATUS.md移除，结果留在.spec-agents/state/EVIDENCE.md；不要在.spec-agents/state/STATUS.md里保留已关闭 的工作段落。
每个提升后的记录都必须写明：
status | scope | applies_when | source Evidence ID | verification
如果替代或冲突了旧知识，还要写 supersedes 或 contradicts。只把知识
放进“看起来合适”的目录，不算完成晋升。
收尾：写终态
learn 是唯一写终态的动作，两层用同一条规则：
- 一个 Slice ——
check验证通过后，把evidence_ref和status: done一起写入。两者必须同时写：只写状态而不留证据，正是这套流程要消灭的 「完成了但没人说得清凭什么」。 - 一个 SPEC —— 三条前置同时成立时写
status: verified：该 SPEC 的每个 Slice 都已done；本次结果的 Evidence 已追加；同一次动作里把它从.spec-agents/state/STATUS.md移除。
对于零个 Slice 的 SPEC，第一条前置——每个 Slice 都已 done——替换为：
Evidence 记录点名该 SPEC 的 issue map 中每一项；若没有 issue map，则点名
其 Verification section 中的每个交付物，并说明这些内容已验证。第三条前置——同一
次动作里从 .spec-agents/state/STATUS.md 移除——由已经不在 .spec-agents/state/STATUS.md 中的 SPEC 满足；第二条不变。
任何一条前置都不按空集成立（vacuously true）来读取。
What ships with it
1 file 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.
- 1mo ago Changed · +29 lines 7c84f6c06202
- 1mo ago First seen · 81 lines · 63 tokens per session scan A f6f958f06e8b
learn is a skill published in the GitHub repository yibie/SPEC-AGENTS.md (130 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 1,646 once invoked, about $0.0003 per session on Opus 5.5. 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
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn). Routes meetings to knowledge-meeting-ingest and short thoughts…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
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…