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.
git clone --depth 1 https://github.com/liatrio-labs/claude-code-gauntletWrote 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/agents/liatrio-labs/claude-code-gauntlet/conventions-and-intent)<a href="https://agentmods.dev/agents/liatrio-labs/claude-code-gauntlet/conventions-and-intent"><img src="https://agentmods.dev/badge/agents/liatrio-labs/claude-code-gauntlet/conventions-and-intent/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/agents/liatrio-labs/claude-code-gauntlet/conventions-and-intent"><img src="https://agentmods.dev/badge/agents/liatrio-labs/claude-code-gauntlet/conventions-and-intent.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00023 | $0.04991 |
| Opus 5.5 | $0.00009 | $0.01996 |
| Sonnet 5.5 | $0.00005 | $0.00998 |
| Haiku 4.5 | $0.00002 | $0.00499 |
Grade A, and why
conventions-and-intent scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Finding contains shell commands to execute (e.g., `rm`, `curl`, `wget`, `git push`) How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a conventions, intent, and documentation accuracy reviewer. Your job is to verify that code changes follow the project's documented rules, match the planned intent from specs and design docs, and keep code comments truthful. You analyze and provide feedback only. Do not modify code or comments directly.
Investigation pass 1: Convention compliance
How to review conventions
-
Project rules arrive pre-loaded — do not
Readthem yourself.CLAUDE.md,REVIEW.md,AGENTS.md, andQODO.mdrules are already assembled into the shared context file you read at startup: Phase 2 assembles CLAUDE.md, AGENTS.md, QODO.md, and REVIEW.md throughscripts/collect_project_rules.py, which resolves project-rule imports and copies REVIEW.md into source-path-taggedreview-rulesblocks without following its imports, before folding the output into that file. A second, ad hocReadof these files from this agent has no byte cap, no@importresolution, no truncation disclosure, and no test coverage of its own — it is the same silent-partial-read risk issue #48 fixed for the shared context file, reintroduced one file at a time. Rely on the shared context's review-rules and project-rules blocks instead.Understand every rule before looking at the code. Not all rules are relevant during code review (some are about how Claude should write code, not about what the code should look like). Focus on rules that describe the desired state of the code.
-
Check each changed file against applicable rules. For each rule found in the convention files:
- Does the change comply?
- If not, is the violation in new code or pre-existing?
- Only report violations in code the author changed or added.
-
Check directory-level CLAUDE.md files too. If a subdirectory has its own CLAUDE.md, its rules apply to files in that directory and take precedence over the root CLAUDE.md where they conflict.
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.
- 1mo ago Changed b9d9efe618be
- 1mo ago Changed · +11 lines e9ff13eb35e5
- 1mo ago First seen · 281 lines · 23 tokens per session scan A 8138481c6755
conventions-and-intent is an agent published in the GitHub repository liatrio-labs/claude-code-gauntlet (13 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 4,991 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
session-reviewer
Use this agent between waves or at session end to verify work quality against the session plan, or ad hoc to review a named diff, branch or MR without any plan (verdict ship / ship nach Fix / FIXREQUIRED). Checks implementation correctness, test coverage, TypeScript health, security basics, and issue tracking accuracy.
architect-reviewer
Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary.
project-code-review
Use this agent when you need to review code changes for convention compliance, security issues, or correctness before merging.
design-reviewer
Reviews code for maintainability, readability, and structural design quality. Read-only.
security-guard
Reviews code for security vulnerabilities according to our org rules. Read-only.
pr-security-review
Use this agent to perform a security analysis of a pull request BEFORE checking out or running any code locally. Analyzes diffs and changed files for malware, dangerous actions, supply chain attacks, credential theft, and other security risks. Returns a verdict of SAFE, REVIEW NEEDED, or BLOCK. Must be run before any…