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 agentmods add skills/tph-kds/deckforge/deckforge-skill-evaluatornpx skills add tph-kds/deckforge --skill deckforge-skill-evaluatorgit clone --depth 1 https://github.com/tph-kds/deckforgeWhat 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 | $0.00061 | $0.00293 |
| Opus 5 | $0.00030 | $0.00147 |
| Sonnet 5 | $0.00012 | $0.00059 |
| Haiku 4.5 | $0.00006 | $0.00029 |
Grade A, and why
deckforge-skill-evaluator 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 2d 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.
What it actually says
deckforge-skill-evaluator
Development evaluator. Grade outcomes, not whether the agent mentioned an internal step.
- Identify the intended outcome.
- Select three to five high-quality tasks from
evals/core-eval-cases.json. - Create baseline, current, and candidate conditions.
- Validate automated graders against reference results.
- Run install, trigger, build, behavior, accessibility, visual, and export assertions.
- Run across supported agents where applicable.
- Blind human reviewers to condition labels.
- Measure quality delta, variance, context cost, runtime, and false claims.
- Analyze failures and revise.
- Block release when critical tasks regress.
Read references/blind-review-protocol.md and assets/quality-rubric.json, plus the
shared contract at ../deckforge/references/skill-evaluation-contract.md. Write results
per ../../schemas/skill-eval-result.schema.json and ../../schemas/trigger-eval-result.schema.json.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 27 lines · 61 tokens per session scan A 2dd887f840fa
deckforge-skill-evaluator is a skill published in the GitHub repository tph-kds/deckforge (4 stars, last pushed 16d ago), licensed MIT. It adds 61 tokens to every session and 293 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
smoke-test
End-to-end smoke test skill for DeerFlow. Guides through: 1) Pulling latest code, 2) Docker OR Local installation and deployment (user preference, default to Local if Docker network issues), 3) Service availability verification, 4) Health check, 5) Final test report. Use when the user says "run smoke test", "smoke…
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
vercel-deploy
Deploy applications and websites to Vercel. Use this skill when the user requests deployment actions such as "Deploy my app", "Deploy this to production", "Create a preview deployment", "Deploy and give me the link", or "Push this live". No authentication required - returns preview URL and claimable deployment link.
engineer-system-change
Evaluate and carry out non-trivial software-system changes from first principles. Use when assessing RFCs, issues, designs, features, refactors, migrations, dependency changes, or proposed fields, events, APIs, modules, and services whose need, consumers, system fit, validation, or rollback require scrutiny. Read the…
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.