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 chimera-thin-vertical-slicegit 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/chimera-thin-vertical-slice)<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/chimera-thin-vertical-slice"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-thin-vertical-slice/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/chimera-thin-vertical-slice"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-thin-vertical-slice.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 | $0.00958 |
| Opus 5 | $0.00018 | $0.00479 |
| Sonnet 5 | $0.00007 | $0.00192 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
chimera-thin-vertical-slice 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trigger
You are starting work that spans layers — a command that reaches an orchestrator that calls a provider that writes to a store — and you are deciding what to build first. The temptation is to build the bottom layer completely, then the next, then wire it up at the end.
It does not apply to work that is genuinely one layer deep: a parser, a formatter, a pure function. There is no vertical there, and inventing one is ceremony. It also does not apply to a change inside a system that already runs end to end; that path exists, and the slice has already been paid for.
Do
- Name the observable the slice will produce, as a command someone else could type and a single
concrete output. Not "the pipeline works" —
chimera run "hi"prints one line that came back from a real provider. - Write that invocation first, as a script or a test, and watch it fail for the right reason.
- Implement the shortest path through every layer, degenerate at each one: one provider, no retry, no config file, no cache, no concurrency. Where a policy will eventually live, put a constant.
- Keep the layer that carries the actual unknown real. If you do not yet know what the provider returns, the provider is the one thing in slice one that must not be a stub.
- Commit at the moment it runs, before generalising. That commit is the evidence that the layers fit together.
- Widen one axis at a time — second provider, then configuration, then caching — and keep the command from step 1 working after each. If it breaks, that widening is the suspect.
Avoid
Designing an interface against zero callers. The horizontal order produces a base class, six adapters, a registry and a retry policy on day one, and discovers at wiring time that the shape is wrong — because nothing had yet asked it a real question.
# Day 1, horizontal: none of this has ever run.
class BaseProvider(ABC): ...
class ProviderRegistry: ...
class RetryPolicy: ...
# Day 1, vertical: ugly, hardcoded, and it answers the question.
def complete(prompt: str) -> str:
return _post(URL, {"model": MODEL, "prompt": prompt})["choices"][0]["text"]
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.
- 10d ago First seen · 87 lines · 37 tokens per session scan A cc2b4e8524f6
chimera-thin-vertical-slice is a skill published in the GitHub repository brcampidelli/chimera-agent (22 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 958 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
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).
llm-wiki
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
authoring-claude-md
Creating and maintaining CLAUDE.md project memory files and .claude/rules/ rule files that provide non-obvious codebase context. Use when (1) creating a new CLAUDE.md for a project, (2) adding architectural patterns or design decisions to existing CLAUDE.md, (3) capturing project-specific conventions that aren't…
find-skills
Helps users discover agent skills from the open skills ecosystem. Use when users ask "how do I do X", "find a skill for X", "is there a skill that can...", or want to extend agent capabilities. This skill searches for and evaluates candidate skills, then presents findings to the user for them to review and decide…