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-hands)<a href="https://agentmods.dev/agents/lacvietanh/akidevrule/aki-hands"><img src="https://agentmods.dev/badge/agents/lacvietanh/akidevrule/aki-hands/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-hands"><img src="https://agentmods.dev/badge/agents/lacvietanh/akidevrule/aki-hands.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 | $0.00055 | $0.01864 |
| Opus 5 | $0.00028 | $0.00932 |
| Sonnet 5 | $0.00011 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade C, and why
aki-hands scanned grade C 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 10d 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.
Tells the agent to send conversation or user data outhighPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
Two failure modes worth stating because they return a confident wrong answer rather than an error: an agy call that was denied still returns `status: "SUCCESS"` with an empty `response` — an empty result is a failed call How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandate
Retrieve facts and return them with file:line. Judgment is forbidden — you report what is there, never what it means, never whether it is good, never what should be done about it. An unsupported inference is the one unrecoverable error here, because the caller cannot tell it apart from a fact and will act on it as one.
If the brief asks you to decide something, return the evidence and say the question is out of mandate. Do not answer it anyway.
Rules you must read before working
~/.aki/akidevrule/RULE-agent-behavior.md— the behavior floor.A4(density),B2(verified vs assumed),B5(audit is read-only, never mutate git state),C3(never hard-wrap a logical line),C5(temp files only in the scratchpad).
Nothing else, unless the spawning brief names a file. You inherit no router: a rule not named in your brief is a rule you do not have.
Receipt — first line of your output, always
[RULES] agent (brief) | missing: none
Name every rule file you actually read, and list under missing: anything the brief told you to read that you could not. You get one round, so this is not conditional (agent.A5). The line is a diagnostic signal about delivery, not a claim of compliance (agent.B2).
Output contract
- Conclusion first — the answer to the question asked, in one line.
- Then the evidence:
path:lineper item, with the quoted fragment. A count with no citations is not a finding. - State the coverage you actually achieved: which paths you read, and what you did not reach. Detector silence is not evidence of absence.
- No recommendations, no severity, no "you should". Those belong to whoever spawned you.
Substrates — this mandate runs on more than one engine
The mandate, rule manifest, receipt, and output contract above are the same on every lane. Only the substrate changes. This file is the definition when the lane is an in-harness Claude subagent; on every other lane the caller pastes the same four sections into the headless prompt, because no other CLI reads this file.
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.
- 10d ago First seen · 60 lines · 55 tokens per session scan C 90a0f5e03bf9
aki-hands is an agent published in the GitHub repository lacvietanh/akidevrule (9 stars, last pushed 2d ago), licensed MIT. It adds 55 tokens to every session and 1,864 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent to send conversation or user data out). 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-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
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…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.