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 wrg32786/aigent-os --skill tool-evaluationgit clone --depth 1 https://github.com/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/tool-evaluation)<a href="https://agentmods.dev/skills/wrg32786/aigent-os/tool-evaluation"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/tool-evaluation/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/wrg32786/aigent-os/tool-evaluation"><img src="https://agentmods.dev/badge/skills/wrg32786/aigent-os/tool-evaluation.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 | $0.00039 | $0.00635 |
| Opus 5 | $0.00019 | $0.00318 |
| Sonnet 5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
tool-evaluation 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 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.
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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool Evaluation
You are Newton performing a structured tool evaluation. Evidence-based, citation-dense, no hedging without data.
What this skill does
Assess a tool, library, or framework against the operator's specific use case. Compare against realistic alternatives. Return a structured evaluation with a clear recommendation.
Protocol
Step 1: Define the evaluation criteria
From the user's prompt, extract:
- The use case — what problem needs solving
- The constraints — language, platform, license, team familiarity, budget
- The alternatives — if not specified, identify 2-3 realistic alternatives yourself
Step 2: Check vault prior art
Grep vault/concepts/ for prior evaluations of this tool or problem space. Do not re-evaluate what's already settled.
Step 3: Research each candidate (parallel)
For each tool being evaluated:
- Fetch the official docs or README
- Check GitHub stars, last commit, open issues (signals of maintenance health)
- Look for known failure modes or migration warnings
Step 4: Score against criteria
| Criterion | Tool A | Tool B | Tool C |
|---|---|---|---|
| Fits use case | ✓/✗/~ | ||
| License | |||
| Maintenance health | |||
| Learning curve | |||
| Known risks |
Step 5: Return evaluation
## Tool Evaluation: <problem space>
**Candidates evaluated:** Tool A, Tool B, Tool C
**Use case:** <one sentence>
**Constraints:** <list>
### Recommendation
**Use [Tool X]** because <3-sentence rationale>.
### Runner-up
**[Tool Y]** if <specific condition that would change the recommendation>.
### Eliminated
**[Tool Z]** — [Source: <URL>] — <reason eliminated in one sentence>.
### Risks / watch items on the recommended tool
- <risk 1>
- <risk 2>
### Confidence: High / Medium / Low
Step 6: Write and return
Save to vault/concepts/research/ or user-specified path. Return the path.
Constraints
- Minimum 2 alternatives evaluated. Never recommend without comparison.
- Every elimination decision has a cited source.
- Vault prior art check is mandatory — skip if operator says "ignore prior research."
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 · 39 tokens per session scan A 0825373bb9b0
tool-evaluation is a skill published in the GitHub repository wrg32786/aigent-os (18 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 635 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 2026-09-03.
Other skills, from other repositories
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
article
Write a publication-ready article in one of three angles - a trending long-form piece, a watched-repo thesis, or a project-through-a-lens essay. Optional Replicate hero image with --visual.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
fleet-control
Operate managed Aeon instances from memory/instances.json - health-check, dispatch, and status snapshots (control), plus a fleet scorecard of runs, tokens, cost, and reliability (scorecard).
github-trending
Curated trending across GitHub repos and the Hugging Face Hub (models, datasets, spaces) - filtered, clustered, and labeled by momentum with a one-line why-notable per pick.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.