Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/xg-gh-25/SwarmAInpx agentmods add skills/xg-gh-25/swarmai/s_evaluateWrote 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/xg-gh-25/swarmai/s_evaluate)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_evaluate"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_evaluate/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/xg-gh-25/swarmai/s_evaluate"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_evaluate.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 | $0.00079 | $0.04065 |
| Opus 5 | $0.00039 | $0.02032 |
| Sonnet 5 | $0.00016 | $0.00813 |
| Haiku 4.5 | $0.00008 | $0.00407 |
Grade A, and why
evaluate 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 10d 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 — 390 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Requirement Evaluation
The "should we?" gate for the lifecycle pipeline. Evaluates any incoming requirement, feature request, or task against the 4 DDD questions before committing pipeline resources.
Works at L0 (structures any request with effort/impact). Gets autonomous judgment at L2 (DDD docs provide strategic alignment, feasibility, and history).
The 4 Questions
Every evaluation answers these, in order:
| # | Question | Source | Without DDD |
|---|---|---|---|
| 1 | Should we do this? | PRODUCT.md (strategic alignment) | Ask the user |
| 2 | Can we do this? | TECH.md (feasibility, constraints) | Estimate from request |
| 3 | Have we tried this? | IMPROVEMENT.md (past lessons) | No historical context |
| 4 | Should we do it now? | PROJECT.md (current priorities) | Assume yes |
Workflow
Step 1: Parse the Request
From the user's message, extract:
- What: one-sentence description of the requirement
- Why: stated motivation or inferred business value
- Who: who benefits (end user, developer, internal team)
- Constraints: deadlines, dependencies, blockers mentioned
If the request is too vague to parse (e.g., "improve things"), ESCALATE immediately:
"I need more specifics to evaluate this. What specifically should improve, and what would success look like?"
Step 2: Score (L2 with DDD docs)
Read the DDD docs and score each dimension 1-5:
Strategic Alignment (PRODUCT.md):
- 5: Directly serves #1 priority
- 4: Serves top-3 priorities
- 3: Aligned but not priority
- 2: Tangentially related
- 1: Not aligned / conflicts with non-goals
Feasibility (TECH.md):
- 5: Trivial — existing pattern, < 1 session
- 4: Straightforward — known approach, 1-2 sessions
- 3: Moderate — some unknowns, 2-4 sessions
- 2: Hard — significant unknowns or new patterns, 4+ sessions
- 1: Very hard — architectural change, cross-cutting, weeks
Historical Lessons (IMPROVEMENT.md):
- Check "What Failed" for similar past attempts
- Check "What Worked" for applicable patterns
- Check "Known Issues" for related problems
- Score 1-5:
- 5: Strong proven pattern — same approach succeeded before
- 4: Related pattern exists — similar approach worked
- 3: No history — neutral (default)
- 2: Weak negative signal — partial failure or abandoned attempt
- 1: Strong negative — same approach tried and failed
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.
- 10d ago First seen · 390 lines · 79 tokens per session scan A 781dd0aaf3a7
evaluate is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 4,065 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
digest
NOTE: this skill requires connected chat / email / project-tracker / docs MCPs, which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Cross-tool rollup of what's pending, what shipped, and what's blocked across chat / email / project tracker /…
roadmap
Render a per-project feature roadmap — a Band×Status grid (Shipped/Current/Next/Later × done/in-progress/blocked/buildable) synthesized from CLAUDE.md + PROGRESS.md, persisted to a committed ROADMAP.md with staleness-aware refresh. Modes: '/roadmap' (nearest project), '/roadmap ' (a projectslist tag), '/roadmap…
stitch
Build or verify cross-repo STITCH.md linking backend + frontends in a product group. Modes: create, verify, diff, section. Uses CODEMAPs as drift source by default. Trigger: '/stitch create ', '/stitch diff '.
aria-assist
Morning product-management review across all your projects. Use when the user runs /aria-assist, asks for a morning review / daily PM digest / "what should I do today across my products", or when the launchd job fires it headless. Two modes - generate (headless: read facts, deep-review ACTIVE projects, apply logged…
backlog
View and manage pending backlog items. Use when user says '/backlog', '/backlog insights', '/backlog clear', 'what's pending', 'show backlogs', 'check backlog status'. (Code port — ADR-094.).
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…