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 ProsusAI/prism --skill curate-skillsgit clone --depth 1 https://github.com/ProsusAI/prismWrote 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/prosusai/prism/curate-skills)<a href="https://agentmods.dev/skills/prosusai/prism/curate-skills"><img src="https://agentmods.dev/badge/skills/prosusai/prism/curate-skills/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/prosusai/prism/curate-skills"><img src="https://agentmods.dev/badge/skills/prosusai/prism/curate-skills.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 | $0.00151 | $0.01881 |
| Opus 5.5 | $0.00060 | $0.00752 |
| Sonnet 5.5 | $0.00030 | $0.00376 |
| Haiku 4.5 | $0.00015 | $0.00188 |
Grade A, and why
curate-skills 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 2mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
Post-extraction cleanup pass over _analysis/extracted_skills_history/ and _analysis/extracted_skills_codebase/. Applies three tests to every existing skill and proposes one of four actions: keep, delete, merge, or rewrite. Produces a curation report and waits for developer confirmation before making any file changes.
Step 1 — Read all extracted skills
Read every SKILL.md file under _analysis/extracted_skills_history/ and _analysis/extracted_skills_codebase/. If both directories are absent or empty, stop:
"No skills found in
_analysis/extracted_skills_history/or_analysis/extracted_skills_codebase/. Run/run-history-pipeline(Claude Code) or@run-history-pipeline(Cursor), or/run-analysis-pipeline(Claude Code) or@run-analysis-pipeline(Cursor), first."
For each skill, record:
- Name and file path (including which directory it came from)
- Description (the full description field — this determines when the skill loads)
- Format: failure-mode skill OR key-decisions skill
- The list of key decisions or failure modes (titles only)
- Status
Do not summarize or collapse at this stage — you need the full content of each skill to apply the tests.
Step 2 — Apply Test 1: Would Claude already know this?
For each skill independently, ask: can the correct decision be derived from official documentation, standard programming principles, or general production engineering knowledge — without having encountered this failure in production?
Apply these three concrete checks:
-
Documentation check — is this behavior explicitly covered in the library or framework's official docs, migration guide, or getting-started tutorial? If the docs say "do X in this situation", the skill adds no value.
-
First-principles check — is this a standard pattern any experienced developer would reach by reasoning? Examples of things Claude already knows: connection pool lifecycle (close() clears a reference, not the pool), async isolation via ContextVar, fail-open for cache reads, RAII patterns, thread-safety in global state.
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.
- 2mo ago First seen · 130 lines · 151 tokens per session scan A 333fa70b606f
curate-skills is a skill published in the GitHub repository ProsusAI/prism (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 151 tokens to every session and 1,881 once invoked, about $0.0006 per session on Opus 5.5. 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.
curate-skills compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| curate-skillsProsusAI/prism | Skill | 20 | 4mo ago | Apache-2.0 | A | 151 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |