What is debug-false-positive?

A debugging process for incorrect Fallow results, including false positives, where something is reported incorrectly, and false negatives, where a real issue is missed.

Use it to reproduce the problem, reduce it to a small test case, inspect extraction through reporting, add a regression test, verify a real project, and review the change.

It traces the result through each processing stage so the fix targets the first incorrect step instead of hiding the symptom in the final output.

debug-false-positive — Skill by fallow-rs

Install

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.

agentmods

npx agentmods add skills/fallow-rs/fallow/debug-false-positive

Any agent

npx skills add fallow-rs/fallow --skill debug-false-positive

Clone the repo

git clone --depth 1 https://github.com/fallow-rs/fallow

Made for: Claude Code, Codex.

Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 178 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00034	$0.00178
Opus 5	$0.00017	$0.00089
Sonnet 5	$0.00007	$0.00036
Haiku 4.5	$0.00003	$0.00018

Measured yesterday against content hash 898ca094c7aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-false-positive 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 yesterday.

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.

.agents/skills/debug-false-positive/SKILL.md · 20 lines

What it actually says

Debug a false result

Reproduce on current main with --format json --quiet.
Reduce to a minimal fixture without losing the behavior.
Trace the finding through extract, resolve, graph, reachability, analysis, suppression, filters, and report assembly.
Fix the earliest incorrect layer.
Add a regression test that fails without the fix.
Run the fixed binary on a real consumer project with a cleared .fallow/ cache and compare old versus new output.
Run review with the affected surface reviewers.

Do not tune expected output around one fixture when the semantic model requires a broader correction.

Changes

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.

yesterday First seen · 20 lines · 34 tokens per session scan A 898ca094c7aa

Subscribe to this mod's changes

debug-false-positive is a skill published in the GitHub repository fallow-rs/fallow (4,429 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 178 once invoked, about $0.0002 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.

Code review Debugging Testing cli code-quality dead-code developer-tools javascript linter

Biome

Biome 2.x — fast all-in-one web toolchain in Rust. Formats, lints, assists. Replaces Prettier + ESLint.

pledgeandgrow/pledge-skills · 33 tokens

eslint-docs

ESLint 10.x — flat config, rules, plugins, formatters, parsers, CLI, Node.js API, custom rules, migration.

pledgeandgrow/pledge-skills · 34 tokens

biome-code-review

Use this skill only when asked to review completed Biome changes in a PR, branch, commit range, diff, or working tree. Perform a read-only static review and report findings without editing files or running project code. Do not use for triage, reproduction, or implementation.

biomejs/biome · 61 tokens

doc-comments

Use this skill whenever writing or editing Rust //, ///, or //! comments in Biome, including comments added incidentally and end-user rustdoc inside lint/assist declarations. For lint/assist rustdoc, also load lint-rule-development for content requirements. Do not use for formatter handling of comments in user code.

biomejs/biome · 70 tokens

type-inference

Use this skill when working on Biome's Salsa-backed JavaScript and TypeScript inference, including type-aware lint rules, raw collection or inferred representations, analyzer requests, tracked queries, import or cycle resolution, profiling, and Salsa invalidation tests. Do not use for standalone CSS/HTML module-graph…

biomejs/biome · 78 tokens

eslint-migrate-options

Use this skill when biome migrate eslint must preserve configurable ESLint rule options through source-option models, Biome conversions, typed rule variants, and migration fixtures. Do not use for generated severity-only mapping or general rule-option design.

biomejs/biome · 53 tokens