chimera-list-exemptions-not-obligations

chimera-list-exemptions-not-obligations is a skill for Claude Code, Codex from brcampidelli/chimera-agent. It costs 50 tokens per session (1,220 once invoked), scanned A, original, Apache-2.0.

A code-review pattern that checks every relevant place where a rule should apply, while recording explicit exceptions. It is intended for codebases where new cases may be added over time.

In plain words
What is it for?
Auditing Python files for required registrations or governance checks, including cases nested inside functions or classes.
Why use it?
A hand-written list can miss a newly added case; scanning the code structure and requiring a reason for each exception makes omissions visible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Auditing Python files for required registrations or governance checks, including cases nested inside functions or classes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brcampidelli/chimera-agent/chimera-list-exemptions-not-obligations
Install

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.

Any agent
npx skills add brcampidelli/chimera-agent --skill chimera-list-exemptions-not-obligations
Clone the repo
git clone --depth 1 https://github.com/brcampidelli/chimera-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for chimera-list-exemptions-not-obligations

README.md
[![agentmods](https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-list-exemptions-not-obligations/github.svg)](https://agentmods.dev/skills/brcampidelli/chimera-agent/chimera-list-exemptions-not-obligations)
Your own site
<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/chimera-list-exemptions-not-obligations"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-list-exemptions-not-obligations/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.

agentmods 80×15 button for chimera-list-exemptions-not-obligations

Your own site · 80×15
<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/chimera-list-exemptions-not-obligations"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/chimera-list-exemptions-not-obligations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,220 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01220
Opus 5 $0.00025 $0.00610
Sonnet 5 $0.00010 $0.00244
Haiku 4.5 $0.00005 $0.00122

Measured 12d ago against content hash 243034feb6f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

chimera-list-exemptions-not-obligations 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 12d 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.

skills/chimera-list-exemptions-not-obligations/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trigger

You are enforcing a property that has to hold at every site of a certain kind: every unattended surface goes through the governance profile, every writer passes the gate, every API route regenerates its schema. The rule is one sentence, but the sites are written at different times by different hands, and none of them calls the thing the others call.

It does not apply when the population is closed by construction — a rule about the three entries of a dispatch table is already enumerated by the table. This pattern earns its cost only when a new site can appear in a file that does not exist yet.

Do

  1. Enumerate the population mechanically. Walk every *.py under the package (PACKAGE.rglob("*.py")), not a hand-written list of the files you happen to know about.
  2. Detect the site structurally. Parse and walk the AST for the call you care about; a grep cannot tell an assembled registry from the same words inside a docstring, and that docstring will exist, because someone will write a comment about the fix.
  3. Walk nested scopes and key by the enclosing chain — chimera/cli/main.py:solve._run_solve. The one surface Chimera lost had its registry built inside a factory() closure (chimera/server/manager.py:_gateway_on_message.factory), invisible to a walk that only looked at top-level functions.
  4. Make the default FAIL. Keep one EXEMPT: dict[str, str] from site key to written reason, and have the assertion list every site found that is not a key in it.
  5. Write the reason as a sentence about that specific site, and separate the kinds of reason. "attended: interactive REPL" (a person can hit Ctrl-C) is a much stronger claim than "assembles an equivalent stack from its own flags" — the second marks a duplicate implementation to consolidate, not a settled answer.
  6. Add a second test asserting every EXEMPT key still names a live site, so the list cannot outlive the code it excuses and rot into a formality.

Read the full file on GitHub · 107 lines

Changes

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.

  1. 12d ago First seen · 107 lines · 50 tokens per session scan A 243034feb6f9

Subscribe to this mod's changes

chimera-list-exemptions-not-obligations is a skill published in the GitHub repository brcampidelli/chimera-agent (25 stars, last pushed today), licensed Apache-2.0. It adds 50 tokens to every session and 1,220 once invoked, about $0.0003 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.