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 agentmods add skills/phantom/phantom-connect-sdk/fix-auditnpx skills add phantom/phantom-connect-sdk --skill fix-auditgit clone --depth 1 https://github.com/phantom/phantom-connect-sdkWrote 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/phantom/phantom-connect-sdk/fix-audit)<a href="https://agentmods.dev/skills/phantom/phantom-connect-sdk/fix-audit"><img src="https://agentmods.dev/badge/skills/phantom/phantom-connect-sdk/fix-audit.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 | $0.00000 | $0.00864 |
| Opus 5 | $0.00000 | $0.00432 |
| Sonnet 5 | $0.00000 | $0.00173 |
| Haiku 4.5 | $0.00000 | $0.00086 |
Grade A, and why
fix-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 3d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: fix-audit
Implement findings from the latest audit report for a package, one item at a time.
Arguments: <package-name> [developer notes] — package name plus optional free-text notes (e.g. "only fix #1", "skip #2, needs discussion", "fix all but use X pattern for #1 instead").
Phase 0 — Load
Find the most recent audit/*-{package-name}*.md (sort by filename date descending). Record this exact filename — it is the audit file for all later steps. Extract unresolved Critical items — an item is resolved if it contains **Resolved or has strikethrough text.
If no unresolved Criticals exist, check developer notes — if they say "important", work the Important tier instead.
Print the final work list before starting any changes.
For each item (work sequentially — fully complete one before starting the next)
Step 1 — Read before touching
Re-read the relevant source files in packages/{package-name}/src/. Verify the bug still exists at the exact file:line the audit references. Apply developer notes if they override the implementation approach.
Step 2 — Implement
Minimal change that fixes exactly what the audit item describes. Rules:
- Never use TypeScript escape hatches (
as any,@ts-ignore,@ts-expect-errorwithout justification) - Never add
eslint-disablecomments to hide a warning caused by the fix - Never skip writing tests
Step 3 — Self-review
Before running tests, ask:
- Does the fix make sense in the full application context?
- Are callers in other packages affected? Check usages with grep across
packages/andexamples/. - Does it change a public contract — exported type, hook return shape, event payload?
- Is there anything the audit item missed that makes the fix incomplete?
Step 3.5 — Write tests first
Write a test that would have failed before the fix and passes now. Assert the exact corrected behaviour. Place the test in the package's existing test file or create a new *.test.ts alongside the changed file.
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.
- 3d ago First seen · 112 lines · 0 tokens per session scan A 89b9dfa764d0
fix-audit is a skill published in the GitHub repository phantom/phantom-connect-sdk (159 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 864 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…