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.
git clone --depth 1 https://github.com/Evol-ai/SkillCompassWrote 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/commands/evol-ai/skillcompass/eval-compare)<a href="https://agentmods.dev/commands/evol-ai/skillcompass/eval-compare"><img src="https://agentmods.dev/badge/commands/evol-ai/skillcompass/eval-compare/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/commands/evol-ai/skillcompass/eval-compare"><img src="https://agentmods.dev/badge/commands/evol-ai/skillcompass/eval-compare.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 | $0.00000 | $0.00753 |
| Opus 5.5 | $0.00000 | $0.00301 |
| Sonnet 5.5 | $0.00000 | $0.00151 |
| Haiku 4.5 | $0.00000 | $0.00075 |
Grade A, and why
eval-compare 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/eval-compare — Version Comparison
Locale: All templates in this spec are written in English. Detect the user's language from the session and translate user-facing text at display time per SKILL.md's Global UX Rules. Dimension labels: see the canonical table in SKILL.md.
Arguments
<version-a>(required): File path or{skill-name}@{version}identifier.<version-b>(required): File path or{skill-name}@{version}identifier.--internal/--ci(optional): Skip interactive choice prompts; output results and exit.
Steps
Step 1: Resolve Versions
For each argument:
- If it's a file path: use the Read tool to load the file directly.
- If it's a
name@versionidentifier: look up.skill-compass/{name}/snapshots/{version}.mdusing the Read tool. - If version not found: output
"Version not found: {identifier}"and stop.
Cross-skill check: If both arguments use name@version syntax and the skill names differ, warn the user that they are comparing different skills ({name_a} vs {name_b}) and the result may lack meaningful reference value, then present the choice:
[Continue comparing / Cancel]
If the user chooses Cancel, stop.
Step 2: Check Cached Results
For each version, check .skill-compass/{name}/manifest.json for cached evaluation results. Use the Read tool to load the manifest.
If cached results exist (matching content_hash): use cached scores. If not: run eval-skill flow on the version to generate fresh results.
Step 3: Compare
Generate a side-by-side comparison:
Version Comparison: sql-optimizer
| Dimension | v1.0.0 | v1.0.0-evo.2 | Delta |
|-----------------|--------|--------------|--------|
| D1 Structure | 6 | 7 | ↑ +1 |
| D2 Trigger | 3 | 6 | ↑ +3 * |
| D3 Security | 2 | 7 | ↑ +5 * |
| D4 Functional | 4 | 4 | → 0 |
| D5 Comparative | 3 | 3 | → 0 |
| D6 Uniqueness | 7 | 7 | → 0 |
|-----------------|--------|--------------|--------|
| Overall | 38 | 52 | ↑ +14 |
| Verdict | FAIL | CAUTION | |
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 · 80 lines · 0 tokens per session scan A ffe4f93f44d6
eval-compare is a command published in the GitHub repository Evol-ai/SkillCompass (215 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 753 tokens. 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 commands, from other repositories
remember
Store something in the appropriate memory file. This command is the smart router for the memory system.
briefing
Morning summary. Show the user where things stand so they can pick up where they left off. This is the "catch me up" command.
reflect
Curate and compress recent memory. This command reviews the last 7 days of journal entries, extracts durable insights, and updates long-term memory files. Think of it as memory maintenance -- moving important things from short-term to long-term storage.
status
Show a comprehensive summary of everything the AI currently knows, plus the health of the search index. This is the "what do you know about me?" command.
qec-setup
Run the guided first-time system setup and diagnostic audit with user approbation safety gate.
qec-facts
Print the verified QECTOR platform fact sheet (surfaces, decoders, code families, MCP entry points, strict-math and honesty rules).