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 SenMuShare/senmu-buildos --skill senmu-build-learninggit clone --depth 1 https://github.com/SenMuShare/senmu-buildosWrote 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/senmushare/senmu-buildos/senmu-build-learning)<a href="https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-learning"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-learning/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/senmushare/senmu-buildos/senmu-build-learning"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-learning.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 | $0.00034 | $0.00468 |
| Opus 5 | $0.00017 | $0.00234 |
| Sonnet 5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
senmu-build-learning 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Organizational Learning
Keep raw feedback, candidate lessons, project rules, and formal BuildOS rules in distinct states. Resolve ordinary corrections in the current task. Load this skill only for inbox review, formal retrospectives, lesson promotion, or knowledge distillation.
Route by Outcome
- Submit or review feedback candidates: Feedback Review.
- Retrospect, deduplicate, promote, or retire resolved lessons: Organizational Learning.
- Promote cross-project improvements into BuildOS: BuildOS Evolution.
- Absorb external Skills/knowledge after current model and host calibration: Knowledge Distillation.
Run the project's validator when modifying formal Lessons Learned. Raw feedback does not need a Lessons ID.
Core Contract
- Capture: Use the local CLI only when BuildOS use in a real project shows that a skill, reference, template, script, hook, or rule caused error, misdirection, execution difficulty, empty guidance, unnecessary work, or inefficiency. Do not capture business requests or ordinary corrections automatically.
- Review: Deduplicate by root cause and classify as
discard,project,buildos_candidate, orneeds_evidence. - Promote: Calibrate against current official guidance for the target model and host. Absorb useful domain capability without importing obsolete prompting workarounds or process overhead. Keep project-specific rules with their owner; promote cross-project meaning with scoped evidence.
Record the component, concrete impact, and evidence or workaround. Dissatisfaction can start a candidate but a vague opinion is insufficient; frequency is not a mechanical threshold. Correct the source first. Do not add prompts, validators, or approvals for every mistake or duplicate a rule across skills, inboxes, logs, and lessons.
What ships with it
8 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.
- agents/openai.yaml 347 B
- assets/learning-governance/LESSONS_LEARNED.template.md 2.3 KB
- assets/learning-governance/RETROSPECTIVE_ENTRY.template.md 597 B
- references/buildos-evolution-and-upstream-feedback.md 5.6 KB
- references/engineering-knowledge-distillation-and-standard-promotion.md 16 KB
- references/feedback-candidates-and-central-adjudication.md 5.8 KB
- references/organizational-learning-and-governance-closure.md 13 KB
- scripts/validate_lessons.py 6.5 KB runs code
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 Changed 03c30c7d1aa3
- 6d ago Changed 6d55d44059b9
- 7d ago Changed · -9 tokens per session a9b1d8e305c5
- 11d ago First seen · 28 lines · 43 tokens per session scan A ead115f8748a
senmu-build-learning is a skill published in the GitHub repository SenMuShare/senmu-buildos (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 34 tokens to every session and 468 once invoked, about $0.0002 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
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
openproject-codex
Use the OpenProject Codex plugin to inspect and manage work in Codex through the OpenProject API.
learn
Knowledge compiler. Extracts patterns, decisions, and anti-patterns from completed campaigns and evolve cycles, then compiles them into structured wiki pages that integrate with existing knowledge rather than appending isolated files. Implements flush→compile→lint pipeline. Auto-triggered by /postmortem and /evolve…
ambient-project
Quietly maintain a useful project view from meaningful work in the current Codex session. Use when work creates a task, bug, decision, idea, risk, milestone, plan, progress update, or explicit completion.
zapier-demo
Walk a new user through setting up their first Zapier action and running it live — the smallest possible win. Asks what app they use, recommends one read action to enable, guides them to mcp.zapier.com to add it, then demonstrates it working in the same chat. Use when the user asks "show me how Zapier works", "set up…
ai-emotional-intelligence
Argues that emotional intelligence becomes strategically critical precisely because of AI -- not despite it -- and provides leaders with practices for developing the soft skills that constitute the human competitive advantage in an AI-saturated economy. Covers empathy, self-awareness, communication beyond technical…