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 agentmods add skills/sanjoy1234/gauntlex/verifynpx skills add sanjoy1234/gauntlex --skill verifygit clone --depth 1 https://github.com/sanjoy1234/gauntlexWrote 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/sanjoy1234/gauntlex/verify)<a href="https://agentmods.dev/skills/sanjoy1234/gauntlex/verify"><img src="https://agentmods.dev/badge/skills/sanjoy1234/gauntlex/verify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00256 |
| Opus 5 | $0.00018 | $0.00128 |
| Sonnet 5 | $0.00007 | $0.00051 |
| Haiku 4.5 | $0.00004 | $0.00026 |
Grade A, and why
gauntlex:verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/gauntlex:verify
Re-derives the report's integrity hash and confirms it matches — proves the artifact has not been altered.
Usage
/gauntlex:verify --run-id <run_id>
Execution
gauntlex verify --run-id "$RUN_ID"
What It Does
- Reads
.gauntlex/reports/<run_id>.json - Extracts the
attacksarray - Re-derives SHA-256 over the JSON-serialized, lexicographically sorted attack array
- Compares against
integrity_hashfield in the report - Exit 0 = match (report is authentic); Exit 1 = mismatch (report tampered)
Output to User
- PASS: "Report <run_id> integrity verified. Hash matches: sha256:"
- FAIL: "TAMPER DETECTED. Expected <stored_hash>, computed <derived_hash>. Do not use this report for compliance."
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.
- 5d ago First seen · 34 lines · 37 tokens per session scan A 4678bbfd8ca9
gauntlex:verify is a skill published in the GitHub repository sanjoy1234/gauntlex (1 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 256 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 2026-08-31.
Other skills, from other repositories
zero-width-injection
A helpful skill that reports the current weather for a city.
skill-tagchars
Fetches the weather forecast for a city. Use this tool when the user asks about weather..
legit-unicode
Finds the nearest café. Supports accents (naïve, résumé) and CJK text: 天気予報。 Use this tool when the user asks to find a café nearby.
reference-cites-example
A skill that teaches an agent to recognize and resist prompt-injection attempts. See references/system-prompt-guide.md for the phrases to watch for.
reference-negated-defensive
Guidance for compacting an agent's working memory safely. See references/memory-guide.md for the authority rules.
markdown-cited-paths
A defensive skill that teaches the agent to recognize prompt-injection and credential-theft attempts in untrusted web snippets. It DESCRIBES the attack patterns as markdown inline-code examples; it does not perform them.