Fallow is a command-line static-analysis tool that builds a dependency graph of TypeScript and JavaScript code to identify unused code, duplication, circular dependencies, complexity hotspots, boundary violations, and styling drift. It is for developers reviewing codebases and verifying changes, with catalogue entries that add agent, editor, and workflow integrations.
Borrowing it
Nothing to install: this file belongs to fallow-rs/fallow. 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/fallow-rs/fallow/main/.agents/skills/perf-loop/SKILL.mdgit clone --depth 1 https://github.com/fallow-rs/fallowWrote 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/fallow-rs/fallow/perf-loop)<a href="https://agentmods.dev/skills/fallow-rs/fallow/perf-loop"><img src="https://agentmods.dev/badge/skills/fallow-rs/fallow/perf-loop/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/fallow-rs/fallow/perf-loop"><img src="https://agentmods.dev/badge/skills/fallow-rs/fallow/perf-loop.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 | $0.00022 | $0.00180 |
| Opus 5.5 | $0.00009 | $0.00072 |
| Sonnet 5.5 | $0.00004 | $0.00036 |
| Haiku 4.5 | $0.00002 | $0.00018 |
Grade A, and why
perf-loop 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 23d 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
Performance loop
- Choose a stable benchmark and preserve its identity and workload. Before you freeze it, prove that it can see the problem: a known slowdown must move the result.
- Record a statistically useful baseline. Set a target and a minimum number of rounds. Do not stop before that minimum unless you reach the target.
- Profile the hot path before editing.
- Implement one bounded optimization.
- Re-run the same benchmark and correctness checks.
- Keep the change only when the improvement is reproducible and no contract regresses.
- Use a new benchmark identifier for a materially different workload.
- Run
review.
Do not report performance gains from debug builds or incomparable fixtures.
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.
- 23d ago Changed · +3 lines 7516c6afa113
- 1mo ago First seen · 19 lines · 22 tokens per session scan A 1e57ef6b5a38
perf-loop is a skill published in the GitHub repository fallow-rs/fallow (5,139 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 180 once invoked, about $0.0001 per session on Opus 5.5. 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
biome
Biome - Fast all-in-one toolchain for web projects (linter + formatter in Rust, 100x faster than ESLint).
argot-check
Score your working changes with argot — flag code foreign to this repo's own patterns (unfamiliar dependencies, APIs, constructs), functions the repo already has, code filed in the wrong place, imports that break the repo's layering, and tests weakened, disabled, or deleted alongside a production change — before…
poly-lint-and-format
Running poly lint / poly fmt — --fix, --format pretty|json|toon, --exclude, --config, exit codes, inline suppression, and the check → read-json → fix → re-check loop.
dispatcher
Use this skill when running a Taniwha build from the main Claude Code session. The skill turns the main session into a thin, mechanical executor that follows instructions from ephemeral orchestrator subagents. Trigger this whenever the user wants to start a Taniwha build, resume an interrupted one, or work on a…
poly-tiers-and-scope
Five mechanisms decide what actually inspects a file (crates/poly-core/src/registry.rs).
poly-overview
What poly is — the native, tree-sitter, native-toolchain, quality, and built-in-rule-pack tiers, language coverage, and when to reach for it.