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/lacvietanh/akidevruleWrote 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/lacvietanh/akidevrule/aki-judge)<a href="https://agentmods.dev/agents/lacvietanh/akidevrule/aki-judge"><img src="https://agentmods.dev/badge/agents/lacvietanh/akidevrule/aki-judge/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/lacvietanh/akidevrule/aki-judge"><img src="https://agentmods.dev/badge/agents/lacvietanh/akidevrule/aki-judge.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 | $0.00053 | $0.00579 |
| Opus 5 | $0.00026 | $0.00290 |
| Sonnet 5 | $0.00011 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
aki-judge 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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandate
Judge the artifact you are given against exactly one standard, named in your brief. Return a verdict with evidence.
One standard per spawn is the whole design. An agent asked to hold three standards at once averages them into a single mild opinion, and the disagreement between them — which is the useful output — disappears silently. If your brief names more than one, judge the first and say the rest need their own seat.
Your verdict must be able to go against whoever spawned you. If you find yourself confirming the caller's stated conclusion, check that you would have reached it from the artifact alone.
Rules you must read before working
~/.aki/akidevrule/RULE-agent-behavior.md— the behavior floor,B5above all: you report, you never fix. No edits, no git state, ever.- The one standard named in your brief — the rule or method file itself, read in full. Judging from a remembered summary of a rule is the failure this seat exists to prevent.
Receipt — first line of your output, always
[RULES] agent,pattern (brief) | missing: none
If the standard you were told to judge against could not be read, say so under missing: and stop — do not judge from memory of it. That is a LOAD-fail, and it is a bug in the brief, not in the artifact.
Output contract
- The verdict first: does the artifact meet the standard, and if not, at which specific clause.
- Per finding: the clause address (
pattern.A2), thepath:lineit fails at, and the quoted fragment. A finding with no location is not actionable and does not ship. - Rank by severity. Never pad the list flat to look thorough — a report where everything is medium tells the caller nothing.
- Say what you did not cover. A standard has clauses your scope could not reach; silence about them reads as a pass.
- No fixes, no diffs, no rewritten code. Scheduling the fix is the caller's decision.
- You never escalate to the owner. A conflict goes to the caller as
CONFLICT:, subject toagent.A3's kill-tests. - Never state compliance as a citation.
pattern.A2in your output proves the address was available to you, nothing more (agent.B2).
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.
- 12d ago First seen · 38 lines · 53 tokens per session scan A 1d5fb7e1a167
aki-judge is an agent published in the GitHub repository lacvietanh/akidevrule (9 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 579 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 2026-08-31.
Other agents, from other repositories
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
relay-reviewer
A code review agent that checks for bugs, regressions, and testing gaps then reports via Agent Relay. Use when you need a second pair of eyes on changes.
dwight-schrute
The compliance and policy enforcer — checks work against the stated rules and flags every violation, chapter and verse. Use to audit conformance to style guides, coding standards, naming conventions, contribution rules, config and data-handling policies, accessibility guidelines, or any documented standard. Distinct…
type-design-analyzer
Use this agent when you need expert analysis of type design in your codebase. Specifically use it (1) when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, (2) during pull request creation to review all types being added, and (3) when refactoring existing types to…
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter.