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/midnightdarling/collate/prometheusnpx skills add MidnightDarling/collate --skill prometheusgit clone --depth 1 https://github.com/MidnightDarling/collateWhat 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 | $0.00037 | $0.00497 |
| Opus 5 | $0.00018 | $0.00249 |
| Sonnet 5 | $0.00007 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
prometheus 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
prometheus
The work this skill is for
prometheus steals the fire of definition.
It takes one concept from a historical text and renders it into a compact, public-facing card: genus, differentia, plain-language gloss, institutional and temporal grounding, and one conceptual spark bright enough to hold in the mind.
The card is not a poster full of effects. It is a definition made visible.
Input
Target: $ARGUMENTS
- concept name (for example
三司,均田,经世,清议) → define it directly - workspace directory → read
<ws>/final.md, extract 3–5 definition-worthy terms, ask which one to render .mdfile → same as workspace mode- empty → ask for a concept or source file
Definition recipe
For the chosen concept, derive:
- Genus and differentia — what kind of thing it is, and what distinguishes it
- Plain gloss — what it means in ordinary language
- Formal signature — a minimal structured definition
- Essential distinction — what nearby concepts it must not be confused with
- Temporal context — dynasty, institution, or discourse that grounds it
- Philosophical core — why the concept matters beyond the glossary level
Rendering contract
Render in ATTRIBUTION-style achromatic discipline:
- one concept = one signal
- no chromatic colour
- title-led composition, quiet grid, wide margin
- body text should remain spare and legible
Output path:
- workspace mode →
<workspace>/analysis/prometheus/{concept}.svg - single-file mode →
analysis/prometheus/{concept}.svg - pure concept mode → ask for a target directory if none is obvious
If the file exists, ask before overwriting.
Guardrails
- Do not steal five flames at once: render one concept per invocation.
- Do not turn the card into a miniature essay.
- The card should clarify, not merely decorate.
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 · 63 lines · 37 tokens per session scan A aa70f4e15ac2
prometheus is a skill published in the GitHub repository MidnightDarling/collate (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 497 once invoked, about $0.0002 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
honey-superpowers
Inject Honey levers into dispatched subagent prompts.
honey-px
Read huge read-only text as PNG pages; big input cut.
honey-ccr
Compress-cache-retrieve huge array tool output.
honey-eco
Report session token and CO2 savings vs no-Honey baseline.
honey-design
Same pixels, fewer tokens: dense CSS for user-facing UI.
honey-memory
Per-project persistent memory files indexed in MEMORY.md.