senmu-build-learning

senmu-build-learning is a skill for Claude Code, Codex from SenMuShare/senmu-buildos. It costs 34 tokens per session (468 once invoked), scanned A, original, Apache-2.0.

A set of rules for reviewing feedback and turning verified lessons into reusable project or organizational guidance. It separates raw feedback, candidate lessons, project rules, and official BuildOS rules.

In plain words
What is it for?
Use it when formally reviewing a feedback inbox, running a retrospective, promoting or retiring lessons, or distilling outside guidance into reusable engineering rules. It is not for routine logs or independent audits.
Why use it?
It prevents ordinary corrections or vague dissatisfaction from becoming permanent process rules. It also helps avoid duplicate lessons and ensures that broader rules have evidence, clear scope, and an owner.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present.

Part of the senmu-buildos plugin — 9 skills, 2 hooks shipped together

Good fit Use it when formally reviewing a feedback inbox, running a retrospective, promoting or retiring lessons, or distilling outside guidance into reusable engineering rules. It is not for routine logs or independent audits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/senmushare/senmu-buildos/senmu-build-learning
Install

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.

Any agent
npx skills add SenMuShare/senmu-buildos --skill senmu-build-learning
Clone the repo
git clone --depth 1 https://github.com/SenMuShare/senmu-buildos

Made for: Claude Code, Codex.

Or install senmu-buildos, the plugin that ships this one along with the rest of its 9 skills, 2 hooks.

Wrote 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.

agentmods badge for senmu-build-learning

README.md
[![agentmods](https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-learning/github.svg)](https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-learning)
Your own site
<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.

agentmods 80×15 button for senmu-build-learning

Your own site · 80×15
<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>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 468 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 03c30c7d1aa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_lessons.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/senmu-build-learning/SKILL.md · 28 lines

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

Run the project's validator when modifying formal Lessons Learned. Raw feedback does not need a Lessons ID.

Core Contract

  1. 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.
  2. Review: Deduplicate by root cause and classify as discard, project, buildos_candidate, or needs_evidence.
  3. 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.

Read the full file on GitHub · 28 lines

Changes

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.

  1. 2d ago Changed 03c30c7d1aa3
  2. 6d ago Changed 6d55d44059b9
  3. 7d ago Changed · -9 tokens per session a9b1d8e305c5
  4. 11d ago First seen · 28 lines · 43 tokens per session scan A ead115f8748a

Subscribe to this mod's changes

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.

Related

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…

shigella520/MindTrain · 115 tokens

openproject-codex

Use the OpenProject Codex plugin to inspect and manage work in Codex through the OpenProject API.

varaprasadreddy9676/openproject-codex-plugin · 27 tokens

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…

SethGammon/Citadel · 66 tokens

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.

Bene-2020/plane-codex-mcp · 46 tokens

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…

zapier/zapier-mcp · 121 tokens

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…

fatihguner/foreman · 127 tokens