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 pjt222/agent-almanac --skill chrysopoeiagit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/chrysopoeia)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/chrysopoeia"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/chrysopoeia/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/pjt222/agent-almanac/chrysopoeia"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/chrysopoeia.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 | $0.00094 | $0.01884 |
| Opus 5.5 | $0.00038 | $0.00754 |
| Sonnet 5.5 | $0.00019 | $0.00377 |
| Haiku 4.5 | $0.00009 | $0.00188 |
Grade A, and why
chrysopoeia 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 1mo 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrysopoeia
Systematically extract maximum value from existing code — identify what's golden (high-value, well-designed), what's lead (resource-heavy, poorly optimized), and what's dross (dead weight). Then amplify the gold, transmute the lead, and remove the dross.
When to Use
- Optimizing a working but sluggish codebase for performance
- Refining an API surface that has accumulated cruft over iterations
- Reducing bundle size, memory footprint, or startup time
- Preparing code for open-source release (extracting the valuable core)
- When code works correctly but doesn't shine — it needs polish, not rewrite
Inputs
- Required: Codebase or module to optimize (file paths)
- Required: Value metric (performance, API clarity, bundle size, readability)
- Optional: Profiling data or benchmarks showing current performance
- Optional: Budget or target (e.g., "reduce bundle by 40%", "sub-100ms response")
- Optional: Constraints (can't change public API, must maintain backward compat)
Procedure
Step 1: Assay — Classify the Material
Systematically classify every element by its value contribution.
- Define the value metric from Inputs (performance, clarity, size, etc.)
- Inventory the codebase elements (functions, modules, exports, dependencies)
- Classify each element:
Value Classification:
+--------+---------------------------------------------------------+
| Gold | High value, well-designed. Amplify and protect. |
| Silver | Good value, minor imperfections. Polish. |
| Lead | Functional but heavy — poor performance, complex API. |
| | Transmute into something lighter. |
| Dross | Dead code, unused exports, vestigial features. |
| | Remove entirely. |
+--------+---------------------------------------------------------+
- For performance optimization, profile first:
- Identify hot paths (where time is spent)
- Identify cold paths (rarely executed code that may be dross)
- Measure memory allocation patterns
- Produce the Assay Report: element-by-element classification with evidence
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.
- 1mo ago First seen · 179 lines · 94 tokens per session scan A e9e20f4f9e5b
chrysopoeia is a skill published in the GitHub repository pjt222/agent-almanac (42 stars, last pushed today), licensed MIT. It adds 94 tokens to every session and 1,884 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
triage-issue
Verify an issue, persisted audit finding, or unresolved review finding against current code, classify it, and write only the contracted forge/ledger outcome. Supports independent batches and a routed review-finding route: a fix-now row is handed to /fold-findings, never implemented here. Triggers: "triage-issue"…
triage-issue-reports
Triage Slack issue reports with one thread-only verdict, evidence review, cause-aware routing, tracker dedupe, and fail-closed ticket creation. Use only from the configured Benny triage automation.
workers-profiling
Profile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
stall
Show CocoStall loop and no-progress detection status.
stall-reset
Reset CocoStall counters after an operator-approved recovery.