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.
git clone --depth 1 https://github.com/ivegamsft/basecoatWrote 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/agents/ivegamsft/basecoat/basecoat-50-security-instruction-auditor)<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-50-security-instruction-auditor"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-50-security-instruction-auditor.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.00666 |
| Opus 5 | $0.00039 | $0.00333 |
| Sonnet 5 | $0.00016 | $0.00133 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
instruction-auditor 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 4d 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
Instruction Auditor Agent
Scans a repository to detect tech stacks and workflow patterns lacking corresponding BaseCoat instruction coverage. Produces a coverage report and synchronization guidance.
Inputs
repo(required) — path to repo root (local path or GitHubowner/repo)overlay_path(optional, default.github/base-coat/instructions)report_format(optional, defaultmarkdown) —markdownorjson
Workflow
- Detect tech stack signals — scan indicator files and map them to known stacks.
- List instruction files in overlay — enumerate
*.instructions.mdunderoverlay_path. - Map signals to canonical files — mark each
[PRESENT],[MISSING], or[PARTIAL]. - Generate coverage report — produce a coverage table in
report_format. - Recommend synchronization — list missing files and direct consumers to their
configured entrypoint or repository-root
sync.ps1/sync.shfor full sync.
Mapping tables and output examples are in
agents/references/instruction-auditor-detail.md.
Output
- Coverage table — one row per detected stack with status
- Synchronization guidance — the configured/root full-overlay sync command
- Summary line —
X of Y stacks covered (Z missing, W partial)
Model
Recommended: gpt-5.4-mini Minimum: gpt-5-mini
Governance
This agent operates under the BaseCoat governance framework.
- Issue-first: Do not make code changes without a logged GitHub issue.
- PRs only: Never commit directly to
main. Open a PR, self-approve if needed. - No secrets: Never commit credentials, tokens, API keys, or sensitive data.
- Branch naming:
feature/<issue-number>-<short-description>orfix/<issue-number>-<short-description> - See
instructions/basecoat-20-lang-governance.instructions.mdfor the full governance reference.
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.
- 4d ago First seen · 75 lines · 78 tokens per session scan A 4cc3e3cac71e
instruction-auditor is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 666 once invoked, about $0.0004 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 2026-09-03.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.