verify-before-claiming

verify-before-claiming is a skill for Claude Code, Codex from brcampidelli/chimera-agent. It costs 31 tokens per session (582 once invoked), scanned A, original, Apache-2.0.

A completion-checking rule for coding agents. It requires the agent to verify an observable result before saying a task is finished.

In plain words
What is it for?
Use it when fixing bugs, changing configuration, editing files, or claiming tests pass. It also clarifies when an explanation or review should finish without requiring a code change.
Why use it?
It prevents plans or explanations from being mistaken for completed work. The agent checks the changed file, command result, or other evidence directly.

Skill for Claude CodeCodex

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

Good fit Use it when fixing bugs, changing configuration, editing files, or claiming tests pass. It also clarifies when an explanation or review should finish without requiring a code change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brcampidelli/chimera-agent/verify-before-claiming
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 verify-before-claiming
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 verify-before-claiming

README.md
[![agentmods](https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/verify-before-claiming/github.svg)](https://agentmods.dev/skills/brcampidelli/chimera-agent/verify-before-claiming)
Your own site
<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/verify-before-claiming"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/verify-before-claiming/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 verify-before-claiming

Your own site · 80×15
<a href="https://agentmods.dev/skills/brcampidelli/chimera-agent/verify-before-claiming"><img src="https://agentmods.dev/badge/skills/brcampidelli/chimera-agent/verify-before-claiming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 582 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 $0.00031 $0.00582
Opus 5 $0.00015 $0.00291
Sonnet 5 $0.00006 $0.00116
Haiku 4.5 $0.00003 $0.00058

Measured 9d ago against content hash 46f8e4562ac4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

verify-before-claiming 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 9d 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/verify-before-claiming/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Trigger

You are about to say a task is complete. Anything from "fixed the bug" to "updated the config" to "the tests should pass now".

It does not apply when the task was genuinely to explain, review or investigate something. Those finish with an answer, and demanding a diff from them is its own mistake.

Do

  1. Name the observable that would be different if the work had happened. A file whose contents changed, a command whose exit code flipped, a row that now exists.
  2. Check that observable. Actually run the command, actually read the file back.
  3. Report what you saw, including the command and its output — not your expectation of it.
  4. If nothing observable changed, say that plainly instead of describing the change you intended.

Avoid

Reporting the plan as the outcome. The failure reads like: "I updated the handler to check the token before branching" — fluent, specific, technically accurate about the intent, and describing an edit that was never written to disk.

It is tempting because a convincing explanation feels like evidence. It is not. The explanation is produced by the same process that would produce it whether or not the edit landed, so it carries no information about whether it did.

Also avoid checking something adjacent to the claim: running the full suite proves the suite passes, which is not the same as proving this change did this thing. Pick the check that would have failed before.

Check

The claim and the evidence describe the same event, and the evidence came from the machine.

Concretely: a diff that is non-empty, a test that failed before and passes now, output pasted rather than paraphrased. If you cannot produce one, the honest report is "I could not verify this", which is a useful thing to say and takes one sentence.

Risk

Over-applied, this turns a two-line documentation fix into a ceremony, and there are tasks whose result genuinely is prose. The cost of the check should stay well under the cost of being wrong.

Read the full file on GitHub · 63 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. 9d ago First seen · 63 lines · 31 tokens per session scan A 46f8e4562ac4

Subscribe to this mod's changes

verify-before-claiming is a skill published in the GitHub repository brcampidelli/chimera-agent (22 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 582 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.