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 AnastasiyaW/codex-claude-code-config --skill verify-thisgit clone --depth 1 https://github.com/AnastasiyaW/codex-claude-code-configWrote 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/anastasiyaw/codex-claude-code-config/verify-this)<a href="https://agentmods.dev/skills/anastasiyaw/codex-claude-code-config/verify-this"><img src="https://agentmods.dev/badge/skills/anastasiyaw/codex-claude-code-config/verify-this.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.01023 |
| Opus 5 | $0.00043 | $0.00511 |
| Sonnet 5 | $0.00017 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
verify-this 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 8d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify This
Verification is a falsifiable comparison, not a recap of what the agent believes it changed. Turn one claim into a measurable check and preserve enough evidence for another agent to repeat it.
Workflow
- Restate the claim as a condition, metric, and threshold. If the claim cannot
be measured, ask for a measurable form or classify it as
INCONCLUSIVE. - Select the smallest local surface that can disprove it.
- Capture a baseline from the parent commit, merge base, current failing reproducer, or unchanged fixture.
- Capture treatment with the same command, data, warmup, environment, and measurement method.
- Compare raw artifacts: test output, timings, screenshots, HTTP responses, traces, profiles, or heap snapshots. Do not compare summaries alone.
- Return exactly one verdict:
VERIFIED,NOT VERIFIED, orINCONCLUSIVE.
Evidence Contract
Record:
- claim and threshold;
- revision or baseline identity for both runs;
- frozen contract and stage identity when this result will feed later work;
- exact commands and input fixture;
- environment differences and skipped checks;
- artifact paths or hashes, with sensitive payloads kept outside public Git;
- the verdict and one short explanation of confounders.
For durable project work, use the repository's existing proof artifact location,
for example .agent/tasks/<task-id>/verification/<claim-slug>/. Temporary or
sensitive evidence may stay outside the repository; retain only safe metadata and
hashes in the project. Never put credentials, private prompts, customer data, or
heap contents in a public checkout.
Verdict Rules
VERIFIED: baseline and treatment move in the predicted direction, meet the stated threshold, and have no material confound.NOT VERIFIED: behavior is unchanged, moves the wrong way, or misses the threshold.INCONCLUSIVE: there is no valid baseline, the signal is too noisy, the command failed, or the environments are not comparable.
Use this output shape:
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.
- 8d ago First seen · 100 lines · 86 tokens per session scan A bda840736184
verify-this is a skill published in the GitHub repository AnastasiyaW/codex-claude-code-config (149 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 1,023 once invoked, about $0.0004 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
eval-harness
Professional Eval Harness Expert skill. Integrate LLM API workflows, safe system prompt guidelines, and agentic workflows.
promptfoo-redteam-setup
Create or refine promptfoo redteam setup configs: purpose, targets, plugins, strategies, frameworks, multi-input target inputs, policy text, grader guidance, contexts, and static-code-derived target/threat mapping. Use when preparing a red team scan plan from live probes, code evidence, or provider configs, or when…
promptfoo-provider-setup
Configure promptfoo providers or redteam targets for hosted models, live HTTP APIs, Python/JavaScript local scripts, agent SDKs, or multi-input systems. Use when connecting promptfoo to the system under test, mapping vars, auth env vars, request bodies, response transforms, or static-code-derived provider wrappers. Do…
promptfoo-redteam-run
Run, rerun, inspect, and QA promptfoo redteam scans from generated redteam YAML or an existing redteam setup config. Use when executing promptfoo redteam eval or promptfoo redteam run, exporting results, triaging attack success rate, grader failures, target errors, filter/rerun commands, reports, or CI gates. Do not…
discount-review
Inspect the discount policy fixture with a repeatable review checklist and helper script.
code-review
Reviews code for bugs, security issues, and best practices.