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 maddhruv/absolute --skill absolute-prunegit clone --depth 1 https://github.com/maddhruv/absoluteWrote 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/maddhruv/absolute/absolute-prune)<a href="https://agentmods.dev/skills/maddhruv/absolute/absolute-prune"><img src="https://agentmods.dev/badge/skills/maddhruv/absolute/absolute-prune/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/maddhruv/absolute/absolute-prune"><img src="https://agentmods.dev/badge/skills/maddhruv/absolute/absolute-prune.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 | $0.00086 | $0.01187 |
| Opus 5.5 | $0.00034 | $0.00475 |
| Sonnet 5.5 | $0.00017 | $0.00237 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
absolute-prune 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 1mo 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start your first response with the ✂️ emoji.
Absolute Prune
Cut dead growth from the repo: unused dependencies, unreferenced exports, unreachable code, orphaned files. Evidence-based — every removal is backed by a tool that proves nothing references it — applied in safe waves with tests green after each.
Runs the shared engine in references/health-engine.md — read it for the
DETECT → SCAN → TRIAGE → FIX → VERIFY → REPORT loop and the safety contract. This file
covers only what's specific to pruning.
When to use
- "Remove dead code", "clean up unused deps", "what can we delete?".
- Bundle/install bloat from packages nothing imports anymore.
- Post-refactor orphans: files and exports left behind after a feature was rerouted.
prune vs simplify: simplify polishes your working git diff. prune sweeps the
whole committed repo for things that are dead repo-wide. Use simplify mid-change;
prune as standing cleanup on green main.
What it scans
Dead dependencies — declared but never imported (and missing deps that are imported but undeclared):
| Ecosystem | Tool |
|---|---|
| JS/TS | depcheck or knip (knip also covers exports/files) |
| Python | deptry |
| Go | go mod tidy (diff), unused module detection |
Dead code — unreferenced exports, unreachable branches, orphaned files:
| Ecosystem | Tool |
|---|---|
| JS/TS | knip (exports/files), ts-prune, eslint no-unused-vars |
| Python | vulture, ruff unused rules |
| Go | deadcode ./..., staticcheck (U1000) |
Prefer tools already in the project. Treat results as candidates — verify each isn't reached via dynamic import, reflection, DI, public API, or a config string before removing.
Risk ranking (TRIAGE)
| Wave | Removal | Default |
|---|---|---|
| 1 | unused devDeps, unreferenced local exports/functions | fix now — lowest risk |
| 2 | unused runtime deps, orphaned internal files | fix this pass after confirming no dynamic ref |
| 3 | anything reachable via public API, plugin system, dynamic require, reflection, or config | gated / usually defer — high false-positive risk |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 123 lines · 86 tokens per session scan A fa5b8d487f89
absolute-prune is a skill published in the GitHub repository maddhruv/absolute (223 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 1,187 once invoked, about $0.0003 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
audit
Run technical quality checks across accessibility, performance, theming, responsive design, and anti-patterns. Generates a scored report with P0-P3 severity ratings and actionable plan. Use when the user wants an accessibility check, performance audit, or technical quality review.
janitor-fix
Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills. Trigger with '/janitor-fix'.
investigating-builds
Use when the user is working with an existing Buildkite CI run and wants to understand, diagnose, or act on it. Strong signals: a buildkite.com URL, the word "buildkite", the bk CLI, the bktide tool, or a reference to a specific pipeline, build, or job. Covers intents like: "why did this build fail", "what's flaking"…
dead-code
Find unused functions and dead code in the codebase.
scientific-debugging
A method for debugging software by observing the problem, forming possible explanations, running small experiments, and then fixing and checking the result.
incremental-refactoring
Safe, incremental codebase refactoring with dependency graph analysis and live dev server verification.