agentmods.dev

senmu-build-assurance

senmu-build-assurance is a skill for Claude Code, Codex from SenMuShare/senmu-buildos. It costs 40 tokens per session (410 once invoked), scanned A, original, Apache-2.0.

An evidence-based review method for producing a documented finding, such as a proof-of-concept, audit, reproduction, or verdict about a disputed cause. It separates observed facts, conclusions, and items that have not been verified.

In plain words
What is it for?
Use it for decision-focused experiments, blind tests, comparisons, reproducible bug investigations, code or architecture reviews, and delivery or governance audits.
Why use it?
It helps prevent guesses from being presented as facts and makes the basis for a conclusion reviewable. It also keeps the review separate from fixing or changing the system.

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

not rated 2repo changed 7d ago A scan 40 tokens original Apache-2.0

Good fit Use it for decision-focused experiments, blind tests, comparisons, reproducible bug investigations, code or architecture reviews, and delivery or governance audits.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/senmushare/senmu-buildos/senmu-build-assurance
View source ↗ SenMuShare/senmu-buildos
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-assurance
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-assurance

README.md
[![agentmods](https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-assurance/github.svg)](https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-assurance)
Your own site
<a href="https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-assurance"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-assurance/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-assurance

Your own site · 80×15
<a href="https://agentmods.dev/skills/senmushare/senmu-buildos/senmu-build-assurance"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/senmu-build-assurance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 410 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 $0.00040 $0.00410
Opus 5 $0.00020 $0.00205
Sonnet 5 $0.00008 $0.00082
Haiku 4.5 $0.00004 $0.00041

Measured 7d ago against content hash 97d2f985335d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

senmu-build-assurance 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_exhaustive_source_review.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-assurance/SKILL.md · 27 lines

What it actually says

Governance Assurance

Operate read-only by default. Freeze the subject, version, scope, and standard; then distinguish facts, inferences, and unknowns with reviewable evidence. Produce a verdict without automatically remediating it.

Route by Outcome

  • For a decision POC, blind test, controlled experiment, ledger, or reproduction, read Reproducible POC Governance.
  • For a code, architecture, governance, delivery, or whole-project review, read Independent Review and Evidence Grading. Use exhaustive_source only when the user explicitly requests every file, function, or existing comment.

Routine consistency checks remain with the domain skill; G3-G4 alone does not activate Assurance. Read only the applicable Engineering reference when an engineering standard is needed.

Core Contract

  • Declare the review as independent, peer, or evidence-based self-review; do not claim independence without demonstrable separation.
  • Record the frozen target, coverage, evidence source and freshness, excluded scope, and stopping conditions.
  • Evidence supports only what it observes. Static analysis, tests, production facts, and independent review are not interchangeable.
  • Seek counterevidence before assigning status, P0-P3, impact, minimum remediation, and re-review conditions.
  • Keep not_assessed, inconclusive, resolved_unverified, and verified_resolved distinct.
  • Review authority does not permit modification, release, deletion, or production changes. Return remediation to its domain owner.

Use the project's durable task owner for multi-stage reviews. Handoffs carry findings, evidence, scope, target outcomes, and re-review conditions, not copied standards.

Files

What ships with it

12 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.

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. 7d ago Changed 97d2f985335d
  2. 8d ago Changed · -7 tokens per session 1868dd394868
  3. 12d ago First seen · 27 lines · 47 tokens per session scan A 8a095ce5f1d3

Subscribe to this mod's changes

senmu-build-assurance is a skill published in the GitHub repository SenMuShare/senmu-buildos (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 40 tokens to every session and 410 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.

Code reviewDebuggingProject Managementai-agentscodexcodex-pluginopenai-codexproject-governance
Related

Other skills, from other repositories

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

code-intelligence-contract

Use when dependency, call-chain, blast-radius, architecture, domain-flow, or unfamiliar-codebase analysis needs an optional vendor-neutral code-intelligence provider.

hoatv2211/GameStudio-CodexKIT · 35 tokens

ast-grep

Code search, analysis, and refactoring using ast-grep (sg). Use for AST-based code modifications, structural search, and linting.

OutlineDriven/odin-codex-plugin · 33 tokens

review-hog-perspective-logic-correctness

The Logic & Correctness review perspective for PostHog Review. Verifies that changed code does what it is supposed to do: business logic, edge cases, data transformations, and query / data-access correctness. Reports correctness issues only; security and performance are separate perspectives.

PostHog/ai-plugin · 65 tokens

review-hog-perspective-performance-reliability

The Performance & Reliability review perspective for PostHog Review. Verifies that changed code will perform and hold up in production: resource efficiency, error handling and recovery, scalability, and operational readiness. Reports performance and reliability issues only.

PostHog/ai-plugin · 56 tokens

grok

Use when Codex must directly operate or troubleshoot the installed grok-plugin-codex MCP capability surface, including CLI/model checks, literal prompt runs or continuations, session inspection or export, and known background-job control. Do not use for bounded repository delegation, implementation, review…

handong66/grok-plugin-codex · 79 tokens