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 lacvietanh/akidevrule --skill akirulegit 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/skills/lacvietanh/akidevrule/akirule)<a href="https://agentmods.dev/skills/lacvietanh/akidevrule/akirule"><img src="https://agentmods.dev/badge/skills/lacvietanh/akidevrule/akirule/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/skills/lacvietanh/akidevrule/akirule"><img src="https://agentmods.dev/badge/skills/lacvietanh/akidevrule/akirule.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00137 | $0.04624 |
| Opus 5 | $0.00068 | $0.02312 |
| Sonnet 5 | $0.00027 | $0.00925 |
| Haiku 4.5 | $0.00014 | $0.00462 |
Grade A, and why
akirule 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 11d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What this skill does and does not guarantee
Nothing in this file is guaranteed to run. A skill loads only when the model chooses to invoke it, so every rule routed below is best-effort.
The rules that must apply unconditionally are not here. index.md, RULE-agent-behavior.md, RULE-coding.md and RULE-pattern-core.md are embedded by the harness through @ imports in ~/.claude/CLAUDE.md, which is read mechanically at session start. Do not move them back into this file: an @ path inside a skill body is not expanded by the harness the way it is inside CLAUDE.md, so declaring them here would look like an import while loading nothing.
The last two used to be routed here as "default ON" Tier 1 entries. That phrasing promised a guarantee the mechanism could not deliver — a file routed by a skill loads only if the model first decides to invoke the skill — and the observed failure was not the rules being read and ignored but never being read at all. Do not re-add them below: they are already in context on every turn, so a signal block for them would only produce a redundant Read.
Addressing scheme (recall only — does not affect routing)
Every rule file is internally organized into groups A/B/C and numbered items 1/2/3… (e.g. coding.B2, stack.C1). topic = the manifest's Topic column in index.md — usually the filename minus its RULE-/METHOD- prefix; the audit methods keep their short topics (flow, zero-trust, subtract). This is a naming convention for referring to a specific rule precisely — it has no effect on which files load or when; that is still governed entirely by the tiers below. Full map: ~/.aki/akidevrule/index.md.
Tier 1 — Contextual loading
Sensitivity bias: when in doubt, load. A false positive (loading an unused file) costs a few tokens. A false negative (missing a rule) causes wrong behavior.
Before responding, scan the user message and any file paths mentioned. For each rule below: if ANY single signal matches → Read that file immediately, before generating a response.
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.
- 11d ago First seen · 155 lines · 137 tokens per session scan A 028fa466a833
akirule is a skill published in the GitHub repository lacvietanh/akidevrule (9 stars, last pushed 3d ago), licensed MIT. It adds 137 tokens to every session and 4,624 once invoked, about $0.0007 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
starfleet-tasks
Task capture, task lifecycle, dashboard topics, and reports via starfleetctl. Load when capturing, working on, or reporting a task, and for all dashboard access.
starfleet-timer
Set timers instead of blocking a session with sleep/watch-loops (e.g. waiting for a GitHub Actions run): the timer fires a comms directive into the fleet at the scheduled time, and the poller injects it into the owning ship's next turn — no background process, no blocking, survives a session restart.
starfleet
Fleet coordination core — comms, board status, concurrency/isolation, and pointers to the themed starfleet- skills. Load when handling inter-ship messages, checking the board, or unsure which starfleet skill applies.
starfleet-github
GitHub PR/CI/backport interaction via starfleetctl (read-only + mutating commands, PR claims, backports). Load when checking PR status/CI, claiming a PR branch, submitting or repairing a PR, or backporting.
starfleet-sessions
Ship session and workspace management — spawning ships, session attach/stop, git worktrees, web console, deployment. Load when launching/administering ships or managing the fleet web console.
doubt-driven-review
In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…