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 synthesizegit 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/synthesize)<a href="https://agentmods.dev/skills/prosusai/prism/synthesize"><img src="https://agentmods.dev/badge/skills/prosusai/prism/synthesize/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/synthesize"><img src="https://agentmods.dev/badge/skills/prosusai/prism/synthesize.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 | $0.00077 | $0.02530 |
| Opus 5 | $0.00039 | $0.01265 |
| Sonnet 5 | $0.00015 | $0.00506 |
| Haiku 4.5 | $0.00008 | $0.00253 |
Grade A, and why
synthesize 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use this skill
Promote qualifying Type 2 seed clusters from _analysis/incidents.md into practice skills. Writes _analysis/extracted_skills_history/{name}/SKILL.md and _analysis/extracted_skills_history/{name}/plugin.json in the current repo with all team-specific details stripped.
Step 1 — Read incidents.md
Read _analysis/incidents.md. This is the required input.
If it doesn't exist, stop and tell the developer:
"
_analysis/incidents.mdnot found. Run/mine-history(Claude Code) or@mine-history(Cursor) first to extract incident clusters from your git history."
Read the file fully. Note each cluster: its name, the directives/findings listed, their dates, and its current status line.
Also check for _analysis/design.md. If it exists, read it fully. Note all findings — both [technology]-tagged and [codebase]-tagged — recording each one's subsystem, category (decision / non-obvious behavior / structural anti-pattern), and the technology or pattern it concerns. Do not skip [codebase]-tagged findings at this stage. If design.md doesn't exist, continue without it.
Pay particular attention to the ## Architectural patterns section of design.md, if present. These are pre-assembled cross-subsystem patterns from Phase 3c of /mine-design (Claude Code) or @mine-design (Cursor). Treat them as first-class candidates with their own promotion path and key-decisions output format (see Step 3 and Step 5).
Individual design seeds that don't reach the assembled-pattern threshold may be better candidates for /synthesize-decisions (Claude Code) or @synthesize-decisions (Cursor). Flag them as such rather than marking them "too thin".
Step 2 — Auto-discover supplementary docs
Without asking the developer, look for documentation that might contain additional failure modes or lessons learned:
ls docs/ 2>/dev/null
ls adr/ 2>/dev/null
ls decisions/ 2>/dev/null
find . -name "ADR*.md" -not -path "*/node_modules/*" 2>/dev/null | head -10
find . -name "ARCHITECTURE*.md" -not -path "*/node_modules/*" 2>/dev/null | head -5
find . -name "CONTRIBUTING*.md" -not -path "*/node_modules/*" 2>/dev/null | head -5
cat CLAUDE.md 2>/dev/null
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 · 267 lines · 77 tokens per session scan A 3950a4d0dccb
synthesize is a skill published in the GitHub repository ProsusAI/prism (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 77 tokens to every session and 2,530 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…