Borrowing it
Nothing to install: this file belongs to cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions/main/.claude/skills/preflight/SKILL.mdgit clone --depth 1 https://github.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-InstructionsWrote 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/cgfixit/azureai-copilotstudio-personalagent-instructions/preflight)<a href="https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/preflight"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/preflight/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/cgfixit/azureai-copilotstudio-personalagent-instructions/preflight"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/preflight.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 | $0.00061 | $0.01328 |
| Opus 5 | $0.00030 | $0.00664 |
| Sonnet 5 | $0.00012 | $0.00266 |
| Haiku 4.5 | $0.00006 | $0.00133 |
Grade A, and why
preflight 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 9d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preflight — local CI mirror
Every blocking CI gate in this repo, runnable locally in seconds. Run this before
every commit that touches a .md file. A commit that fails preflight will fail CI;
worse, a secret that reaches history is permanent (Gitleaks scans every commit ever
made, so "fixed in the next commit" does not un-fail CI).
Step 1: Run the checker
bash .claude/skills/preflight/check.sh .
Exit 0 = safe to commit. Exit 1 = fix the listed FAILs first. WARN/SKIP lines are informational and mirror the checks CI deliberately runs as non-blocking.
Step 2: Fix failures — check ID → rule → remediation
| Check | Rule it enforces (CLAUDE.md) | How to fix |
|---|---|---|
| C1 unfilled placeholder in an example | "No leftover [UPPER_SNAKE_CASE] tokens in examples/" |
Replace the token with a concrete, domain-appropriate value. If it's genuinely structural syntax, see Forbidden remediations below before touching the exclusion list. |
| C2 TEMPLATE.md token count below floor | "TEMPLATE.md placeholders must remain unfilled — it is the generic source" | Restore the filled-in tokens from git diff TEMPLATE.md. If you deliberately removed placeholders as part of an approved template change, update the expected count comment in check.sh in the same commit and say so in the PR body. |
| C3 missing core invariant | "Dialect variation is tolerated; invariant omission is not" | Add the missing section in that file's own dialect (see the dialect map in CLAUDE.md). Copy the shape from TEMPLATE.md or examples/incident-response.md, then adapt wording to the file's style. |
| C4 chat artifact near end of file | "Instruction files must read as system prompts end-to-end" | Delete the conversational sentence(s). They are output from the chat session that produced the file, not part of the deliverable. |
| C5 secret-shaped string | "Never commit anything that looks like a real secret — Gitleaks scans full history" | Replace with an obviously fake value (your-api-key-here, [email protected], <YOUR_TOKEN>). Never use realistic formats, even invented ones. |
| C6 README out of sync | "The sync triangle: examples/ ↔ Repository Structure ↔ license block ↔ Version History, same commit" | Add/correct the README entry (case-exact filenames). If README references a file that doesn't exist, determine which side is wrong before editing — see Forbidden remediations. |
| C7 markdownlint issues | CI runs this non-blocking by documented decision | Optional cleanup. Do not make the CI job blocking to "enforce" it. |
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.
- 9d ago First seen · 80 lines · 61 tokens per session scan A 7dd55646394b
preflight is a skill published in the GitHub repository cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions (1 stars, last pushed 7d ago), licensed MIT. It adds 61 tokens to every session and 1,328 once invoked, about $0.0003 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
omh-deploy-and-monitor
This is a Hermes-native deploy-and-monitor workflow skill.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).
research-archival
Scrape AI research URLs, archive with frontmatter, create GitHub Issues with identity verification.
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
monorepo-navigator
Inspect or improve Turborepo, Nx, pnpm, or Lerna monorepos: package boundaries, dependency graphs, selective tests, caching, and migrations.
recording-change-intent
Requires an externalised rationale for high-risk changes - new public exports, new endpoints, auth edits, migrations, removed guards - recorded as an Intent commit trailer, an ADR reference, or a module intent register, and reports high-risk changes that carry none. Use when agent-generated or AI-assisted changes ship…