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 brcampidelli/chimera-agent --skill derive-instead-of-transcribinggit clone --depth 1 https://github.com/brcampidelli/chimera-agentWrote 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/brcampidelli/chimera-agent/derive-instead-of-transcribing)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/derive-instead-of-transcribing"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/derive-instead-of-transcribing/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/brcampidelli/chimera-agent/derive-instead-of-transcribing"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/derive-instead-of-transcribing.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 | $0.00037 | $0.00565 |
| Opus 5 | $0.00018 | $0.00282 |
| Sonnet 5 | $0.00007 | $0.00113 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
derive-instead-of-transcribing 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 11d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
Two places in your system hold the same information: a config and its documentation, a schema and its client types, a palette and the site that uses it, a command list and a reference page.
It does not apply when the second copy is deliberately different — a curated getting-started guide is not a stale copy of the reference, it is prose with a different job.
Do
- Pick which one is the source. Usually the one the program actually reads at runtime.
- Generate the other, committing the generated file so diffs are reviewable.
- Add a CI step that regenerates and fails if the committed copy differs, with the exact command to run in the error message.
- Stamp the generated file with the version or commit it was generated from, so a reader knows what it describes.
Avoid
Keeping the copy in sync by remembering. That works while one person holds both files in their head, and stops the first week somebody else touches one of them.
Avoid also the halfway version: generating the file but not gating it. An artefact that is sometimes regenerated is worse than a hand-written one, because it carries the authority of being generated while being just as stale.
And avoid generating prose. Reference material generates well; explanation does not, and a page of mechanically-expanded field descriptions is a page nobody reads.
Check
Change the source, do not regenerate, and push. CI must go red and tell you what to run.
Then read the generated file for the thing you changed and confirm it is there — the gate proves the file is current, not that the generator captured the field you care about.
Risk
A generated artefact that nobody can read defeats the purpose; if the output is only meaningful to a machine, it needs a rendering layer, which is more code to maintain.
There is also a coupling cost. The consumer now depends on the producer's shape, and a refactor on one side breaks a build on the other. That is usually the point — but it means the gate has to be easy to satisfy, or someone will disable it during an unrelated refactor and forget.
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.
- 11d ago First seen · 62 lines · 37 tokens per session scan A 8b9a25705790
derive-instead-of-transcribing is a skill published in the GitHub repository brcampidelli/chimera-agent (23 stars, last pushed today), licensed Apache-2.0. It adds 37 tokens to every session and 565 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 2026-08-30.
Other skills, from other repositories
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
synthesize-report
Produces a citation-grounded summary across one or more workspace source files for summaries, briefings, literature reviews, or comparisons.
data-analysis
Statistical data analysis skill — use when the user asks to analyze numbers, compute statistics, or summarize datasets.
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).