Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add V-Songbird/foundry/plugin install razorWrote 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/v-songbird/foundry/razor-unused)<a href="https://agentmods.dev/skills/v-songbird/foundry/razor-unused"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/razor-unused/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/v-songbird/foundry/razor-unused"><img src="https://agentmods.dev/badge/skills/v-songbird/foundry/razor-unused.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.00858 |
| Opus 5 | $0.00023 | $0.00429 |
| Sonnet 5 | $0.00009 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
razor-unused scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
razor:unused
Runs a mechanical audit — declared dependencies (package.json, requirements.txt/pyproject.toml) with no matching import anywhere in the project's source — and presents the findings. Never removes a dependency itself; the user decides.
1. Run the script
node "${CLAUDE_PLUGIN_ROOT}/scripts/unused-deps.js" <projectDir>
Default <projectDir> to the current working directory if the user didn't name one. The script:
- reads declared deps for whichever ecosystems have a manifest present (node, python — the ecosystems razor's gates already cover),
- walks source files (skipping
node_modules,dist,.git, and other generated/vendored dirs; test files ARE included — a test-only import still counts as used), - normalizes declared names against import roots in the suppressing direction (e.g.
python-dotenvcounts as used when the code importsdotenv) — a false "unused" is the failure mode the script avoids, not the one it risks, - splits misses into two buckets: unused (no mention anywhere — source imports,
package.jsonscripts, or a root config file) and needs a resolver-grade check (the name turns up in a script or config file — eslint/babel/webpack/vite/jest/etc. — or is a@types/*/toolchain dep, meaning it's likely invoked as a CLI tool, plugin, or type-only package rather than imported).
For a node project, the script also detects whether knip is installed or resolvable from the target project. Grep genuinely cannot resolve four classes: binaries invoked from package.json scripts, config-only plugins, true @types pairing, and dependencies that only satisfy another package's peerDependencies (this last one can produce a false "unused" verdict, since grep has no visibility into installed packages' own manifests). When knip is present, the report names it by name as the authoritative escalation for those classes. When it isn't, the report says nothing about it — razor never suggests installing a new tool into the target project.
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.
- today First seen · 40 lines · 45 tokens per session scan A f056d6bcde5b
razor-unused is a skill published in the GitHub repository V-Songbird/foundry (4 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 858 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 2026-09-10.
Other skills, from other repositories
reflect
Self-assessment of AI session quality. Scores 5 dimensions from session data and harness memory. Not an agent performance review — it's human self-reflection on how well they used AI assistance. Use when the user says "reflect", "how did I do", "session review", or at the end of a long session.
systematic-debugging
Systematic debugging approach for errors, test failures, and unexpected behavior. Use when encountering bugs, test failures, errors, or when debugging is needed. Prevents common anti-patterns like random fixes, skipping root cause analysis, and thrashing.
engineering-health
Use when an EM wants to assess engineering systems and processes—not team morale (that's team-diagnosis): measurement, developer experience, onboarding friction, and platform investment. Trigger phrases include "is my team actually productive", "I want to understand developer experience on my team", "how do I measure…
patterns-watch
Use to surface unsolicited patterns across stakeholder reflections, wins log, and self-reflect entries. Trigger phrases include "what patterns am I missing", "anything notable across my files", "scan my reflections for things I should know", "weekly cross-cutting check". Distinct from stakeholder-synthesize…
wins-curate
Use to turn the wins log into an audience-specific artifact — promo packet, behavioral interview stories (STAR), perf-review self-eval, salary case, or year-in-review. Trigger phrases include "build my promo packet", "I have a behavioral interview Tuesday", "draft my self-eval for the perf review", "make a case for a…
read-the-room
Use for retrospective subtext reads on meetings, reviews, Slack threads, or 1:1s. Trigger phrases include "what was actually going on in that meeting", "I think X is bothered but I can't tell why", "did anyone push back on my idea or were they just being polite", "read this Slack thread for me", "is the team aligned…