Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/floomhq/starter/floom-skill-evals)<a href="https://agentmods.dev/skills/floomhq/starter/floom-skill-evals"><img src="https://agentmods.dev/badge/skills/floomhq/starter/floom-skill-evals.svg" alt="Measured on agentmods" 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 | $0.00057 | $0.00620 |
| Opus 5 | $0.00028 | $0.00310 |
| Sonnet 5 | $0.00011 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
floom-skill-evals 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 5d 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.
Floom Skill Evals
Run simple, deterministic skill receipts:
- Create eval tasks for a skill.
- Run baseline and with-skill conditions in isolated Docker workspaces.
- Grade with deterministic verifier.
- Save
result.jsonand a markdown receipt.
When to use
Use this skill for requests like:
- "evaluate this skill"
- "baseline vs with skill"
- "run skill receipts"
- "prove skill lift"
- "Floom Verified style run"
Commands
1) Scaffold an eval task
python3 scripts/scaffold_eval_task.py \
--skill seo-audit \
--task technical-homepage-audit \
--out ./skills/seo-audit/evals
This creates:
<out>/<task>/task.md<out>/<task>/input/<out>/<task>/expected.json<out>/<task>/verifier.py<out>/<task>/eval.json
2) Run A/B eval
python3 scripts/run_skill_eval.py \
--eval-dir ./skills/seo-audit/evals/technical-homepage-audit \
--skill-path ~/.codex/skills/seo-audit \
--agent codex
Outputs:
runs/<timestamp>/result.jsonruns/<timestamp>/report.md- condition workspaces and logs
Default policy rejects scripted output commands (echo, printf, heredoc writes) in agent_command.
Use --allow-scripted only for runner plumbing tests.
Execution model
baseline: run agent command without skill mount.with_skill: run same command with skill mounted at/skilland envFLOOM_SKILL_PATH=/skill.verifier: runs deterministic checker inside each condition workspace.audit: simple deterministic summary from pass/fail/runtime deltas.
Required eval contract
eval.json must include:
idskilltimeout_minutestrialsagentagent_command.baselineagent_command.with_skillverifierexpected_output
Command placeholders supported:
{task_dir}mounted as/task{output_path}path in workspace where agent writes result
Notes
- This v0 runner is Docker-first and local-first.
- Host keeps credentials; container only gets mounted task workspace.
- If API keys are needed, pass scoped env explicitly with
--pass-env OPENAI_API_KEYetc. - Receipts include provenance hashes for verifier and both condition commands.
What ships with it
31 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.
- references/evals/seo-internal-link-architecture/eval.json 705 B
- references/evals/seo-internal-link-architecture/expected.json 133 B
- references/evals/seo-internal-link-architecture/input/links.csv 110 B
- references/evals/seo-internal-link-architecture/input/pages.txt 63 B
- references/evals/seo-internal-link-architecture/task.md 243 B
- references/evals/seo-internal-link-architecture/verifier.py 991 B runs code
- references/evals/seo-meta-canonical-robots/eval.json 1.5 KB
- references/evals/seo-meta-canonical-robots/expected.json 780 B
- references/evals/seo-meta-canonical-robots/input/site/blog.html 152 B
- references/evals/seo-meta-canonical-robots/input/site/index.html 247 B
- references/evals/seo-meta-canonical-robots/input/site/pricing.html 124 B
- references/evals/seo-meta-canonical-robots/input/site/robots.txt 79 B
- references/evals/seo-meta-canonical-robots/input/site/sitemap.xml 128 B
- references/evals/seo-meta-canonical-robots/task.md 609 B
- references/evals/seo-meta-canonical-robots/verifier.py 854 B runs code
- references/evals/seo-pack-summary-20260511T224152Z.json 629 B
- references/evals/seo-pack-summary-20260511T224300Z.json 569 B
- references/evals/seo-structured-data-validation/eval.json 1.0 KB
- references/evals/seo-structured-data-validation/expected.json 382 B
- references/evals/seo-structured-data-validation/input/site/article1.jsonld 82 B
- references/evals/seo-structured-data-validation/input/site/article2.jsonld 89 B
- references/evals/seo-structured-data-validation/input/site/bad.jsonld 52 B
- references/evals/seo-structured-data-validation/input/site/org.jsonld 57 B
- references/evals/seo-structured-data-validation/task.md 330 B
- references/evals/seo-structured-data-validation/verifier.py 834 B runs code
- references/evals/technical-homepage-audit/eval.json 635 B
- references/evals/technical-homepage-audit/expected.json 92 B
- references/evals/technical-homepage-audit/task.md 193 B
- references/evals/technical-homepage-audit/verifier.py 741 B runs code
- scripts/run_skill_eval.py 9.6 KB runs code
- scripts/scaffold_eval_task.py 3.1 KB runs code
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.
- 5d ago First seen · 91 lines · 57 tokens per session scan A 2a50452a1322
floom-skill-evals is a skill published in the GitHub repository floomhq/starter (3 stars, last pushed 3mo ago), licensed MIT. It adds 57 tokens to every session and 620 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
manuscript-reframe
Reframe report-like academic drafts into paper-form scientific arguments while preserving or explicitly renegotiating author intent; requires an approved old-versus-proposed spine, evidence and argument baselines, analysis-role control, and post-edit drift review.
audit
Use when checking a thesis draft before submission for inconsistent numbers, terminology, cross-references, or citation problems.
evidence-review
Build evidence-controlled literature reviews and gap maps with source-status labels, claim registers, citation-role plans, traceability tables, and overclaim audits. Use when drafting or auditing review papers, thesis literature reviews, scoping reviews, or evidence syntheses where adjacent-domain evidence, candidate…
peer-review
Review another author's manuscript, paper, thesis chapter, proposal, or preprint as an external reviewer. Use when asked to evaluate novelty, significance, gap-contribution fit, claim-evidence adequacy, methods, evaluation, overclaim risks, structure, writing, required revisions, or recommendation without rewriting…
revision-escalation
Stop repeated failed writing, coding, manuscript, rebuttal, or restructuring revisions when the same issue has gone through 3+ unsatisfactory edits, vague feedback such as still wrong/weird/unclear/weak/越改越乱, version contamination, or possible gap/claim/evidence/venue-fit drift.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.