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 ignaciohermosillacornejo/copilot-money-mcp --skill boundary-auditgit clone --depth 1 https://github.com/ignaciohermosillacornejo/copilot-money-mcpWrote 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/ignaciohermosillacornejo/copilot-money-mcp/boundary-audit)<a href="https://agentmods.dev/skills/ignaciohermosillacornejo/copilot-money-mcp/boundary-audit"><img src="https://agentmods.dev/badge/skills/ignaciohermosillacornejo/copilot-money-mcp/boundary-audit/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/ignaciohermosillacornejo/copilot-money-mcp/boundary-audit"><img src="https://agentmods.dev/badge/skills/ignaciohermosillacornejo/copilot-money-mcp/boundary-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.02498 |
| Opus 5 | $0.00040 | $0.01249 |
| Sonnet 5 | $0.00016 | $0.00500 |
| Haiku 4.5 | $0.00008 | $0.00250 |
Grade A, and why
boundary-audit 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 12d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Boundary Audit
Quarterly assumption audit (Epic D, issue #445). Gates catch anticipated drift;
this ritual catches the unanticipated. It reads the conformance ledger
(src/conformance/ledger.ts), the codebase, and recent GitHub history — never
the user's financial data.
When to use
- A quarter (~90 days) has passed since the newest report in
docs/audits/ - After a boundary incident (a bug caused by Copilot's server or cache drifting from our local model), to retro-check the whole boundary, not just the incident
- The user says "boundary audit" or asks how trustworthy our external assumptions currently are
Do NOT use if
- The user wants to verify one specific enum/field against production → run the
relevant
scripts/smoke/script (bun run smoke) instead - The user wants to audit their transactions or finances →
/finance-cleanupor/finance-pulse; this skill never touches financial data
Guardrails
- Read-only toward Copilot. The audit reads source, the ledger, and GitHub.
Never call MCP write tools, never run live probes against
app.copilot.money— if an assumption needs a live probe, that is a filed follow-up issue, not an audit step. - The report is committed — PII rules apply. No real financial figures, account balances, account names, or transaction details anywhere in the report or in filed issues. The audit's subject matter is schemas and processes, so this should be natural; if an example needs a figure, use a placeholder ("$X", synthetic numbers).
- Findings become issues, not inline fixes. The audit PR contains the report (and nothing else). Every actionable finding is filed as a GitHub issue; fixing them happens in their own PRs. Exception: none — even one-line doc staleness gets an issue, so the report's findings list and the issue tracker stay 1:1.
- Dedupe before filing. Search open issues (
gh issue list --search) before creating one; if an existing issue covers the finding, reference it in the report instead of filing a duplicate. - No invented history. Phase 3 reviews only PRs/issues that actually exist; quote numbers, not memories.
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.
- 12d ago First seen · 222 lines · 80 tokens per session scan A c39303a00699
boundary-audit is a skill published in the GitHub repository ignaciohermosillacornejo/copilot-money-mcp (79 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 2,498 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 2026-08-30.
Other skills, from other repositories
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
widen-return-type
When delegating a task affected by this skill, include.
opengeni-sites
Build, edit, and publish OpenGeni Sites. Proactively recommend Sites for visual or interactive deliverables such as dashboards, explorable reports, landing pages, demos, trackers, portals, directories, calculators, forms, and custom agent interfaces—even when the user doesn't name Sites. Prefer Sites when the delivery…
refactor-module
Transform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.