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 asyncswap/skills --skill evolve-the-filegit clone --depth 1 https://github.com/asyncswap/skillsWrote 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/asyncswap/skills/evolve-the-file)<a href="https://agentmods.dev/skills/asyncswap/skills/evolve-the-file"><img src="https://agentmods.dev/badge/skills/asyncswap/skills/evolve-the-file.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 | $0.00053 | $0.00781 |
| Opus 5 | $0.00026 | $0.00391 |
| Sonnet 5 | $0.00011 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
evolve-the-file 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 6d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sequence of edits with didChange:
didChange: sends snapshots of the file content via textDocument/didChange between iterations. Each step has its own (line, col) because edits shift positions.
Simple
methods:
textDocument/references:
line: 70
col: 27
didChange:
- file: target.v2.snapshot
line: 69
col: 27
- file: target.v3.snapshot
line: 69
col: 27
The bench runs the method N+1 times (baseline + one per snapshot). Each snapshot file holds the full edited content; the bench buffers it via didChange so the LSP recompiles before the next request.
Why per-step (line, col)
When the edit inserts code above your cursor, the original line shifts. The skill conventionally annotates each step with a comment explaining the shift:
methods:
textDocument/definition:
line: 137 # PRICE — immutable declared at line 68
col: 32
didChange:
- file: Shop.v2.snapshot
line: 142
col: 32
# PRICE shifted (getPrice added above)
- file: Shop.v3.snapshot
line: 138
col: 32
# PRICE same offset (event/error added at bottom — below cursor)
- file: Shop.v4.snapshot
line: 144
col: 32
# PRICE shifted (both edits combined)
Stable cursor (cursor above all edits)
If the cursor sits above every edit, positions stay constant — useful for checking response stability:
methods:
textDocument/hover:
line: 42
col: 13
# addTax — function in library section, above all edits
didChange:
- { file: target.v2.snapshot, line: 41, col: 13 }
- { file: target.v3.snapshot, line: 41, col: 13 }
- { file: target.v4.snapshot, line: 41, col: 13 }
(The line shifts by 1 because the snapshot file itself differs — adjust to match.)
Per-step expect:
Combine with expect: to assert how the response evolves:
methods:
textDocument/references:
expect: { minCount: 14 } # baseline
didChange:
- file: target.v2.snapshot
expect: { minCount: 14 } # same — edit added no new refs
- file: target.v3.snapshot
expect: { minCount: 16 } # +2 new usages
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.
- 6d ago First seen · 90 lines · 53 tokens per session scan A f3052a801e75
evolve-the-file is a skill published in the GitHub repository asyncswap/skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 53 tokens to every session and 781 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
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
validate-album
Validates album directory structure, file locations, and content integrity. Use before release or whenever the user wants to check an album's structural health.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-jest-migration
Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.