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 fabioc-aloha/Alex_Skill_Mall --skill capability-signature-detectiongit clone --depth 1 https://github.com/fabioc-aloha/Alex_Skill_MallWrote 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/fabioc-aloha/alex_skill_mall/capability-signature-detection)<a href="https://agentmods.dev/skills/fabioc-aloha/alex_skill_mall/capability-signature-detection"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/capability-signature-detection/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/fabioc-aloha/alex_skill_mall/capability-signature-detection"><img src="https://agentmods.dev/badge/skills/fabioc-aloha/alex_skill_mall/capability-signature-detection.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 | $0.00020 | $0.00606 |
| Opus 5 | $0.00010 | $0.00303 |
| Sonnet 5 | $0.00004 | $0.00121 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
capability-signature-detection scanned grade A with 1 finding 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 9d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
// Detect: "files that import child_process AND call execFileSync/spawn" How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capability Signature Detection
The Problem
Code-scanning regex that looks for literal strings misses real usage:
// First attempt: find files that use ".github/muscles/"
grep -rn '\.github/muscles/' . // Misses most actual usage!
// Because real code uses variables:
const musclePath = path.join(brainDir, 'muscles', name);
execFileSync('node', [musclePath]); // No literal string!
The Solution
Detect the capability signature, not the literal text.
// Instead of: "files containing '.github/muscles/'"
// Detect: "files that import child_process AND call execFileSync/spawn"
const hasCapability = (content) => {
const importsChildProcess = /require\(['"]child_process['"]\)|from ['"]child_process['"]/.test(content);
const callsExec = /exec(File)?Sync|spawn(Sync)?/.test(content);
return importsChildProcess && callsExec;
};
Pattern Design
Ask: "If a developer renames a path constant, would the test still find them?"
| Approach | Survives Rename? | Use When |
|---|---|---|
| Literal string match | No | String IS the contract |
| Import + call pattern | Yes | Behavior IS the contract |
| AST parsing | Yes | Complex patterns |
Examples
Find Files That Execute Node Scripts
// Bad: misses variable paths
const bad = /execFileSync\(['"]node['"],\s*\[['"]\.github/;
// Good: finds capability
const good = (content) => {
const hasChildProcess = /child_process/.test(content);
const executesNode = /exec(File)?Sync\(\s*['"]node['"]/.test(content);
return hasChildProcess && executesNode;
};
Find Files That Make HTTP Requests
// Bad: misses axios, got, node-fetch, etc.
const bad = /fetch\(/;
// Good: covers common HTTP libraries
const good = (content) => {
return /require\(['"](?:axios|got|node-fetch|undici)['"]\)|fetch\(|http\.request/.test(content);
};
Verification
- Rename a path variable → test still finds the file
- Add new caller with different variable name → test finds it
- False positives are acceptable if they're related capability
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.
- 9d ago First seen · 91 lines · 20 tokens per session scan A fca169cd005d
capability-signature-detection is a skill published in the GitHub repository fabioc-aloha/Alex_Skill_Mall (4 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 606 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
apply-fishbone-diagram
Use when investigating the root cause of a quality defect, recurring process failure, or operational problem — to map all contributing causes across multiple categories simultaneously before selecting which cause to address.
apply-early-intervention
Use when you detect early warning signals — technical debt accumulating, customer relationship cooling, team friction forming, process degrading — to intervene while the problem is still small and cheap, because intervention cost increases nonlinearly with delay.
diagnose-battery-charging-problem
Use when a vehicle has starting problems, battery warning lights, or electrical symptoms — systematically testing battery condition, alternator output, and charging circuit integrity to identify the root cause before replacing components.
diagnose-electrical-fault
Use when a vehicle has a blown fuse, inoperative accessory, warning light, or intermittent electrical failure — applying a systematic test sequence (visual, OBD-II codes, voltage/continuity testing) to isolate the fault to a specific component or circuit without replacing parts blindly.
diagnose-brake-system-problem
Use when experiencing brake warning signs such as noise, pulsation, pulling, soft pedal, or brake warning light to identify the fault before driving or seeking repair.
diagnose-check-engine-light
Use when a check engine light is illuminated and you need to identify the fault code, assess severity, and decide next steps.