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 ikenga-hq/ikenga-pkgs --skill akukogit clone --depth 1 https://github.com/ikenga-hq/ikenga-pkgsWrote 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/ikenga-hq/ikenga-pkgs/akuko)<a href="https://agentmods.dev/skills/ikenga-hq/ikenga-pkgs/akuko"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/akuko/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/ikenga-hq/ikenga-pkgs/akuko"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/akuko.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 | $0.00216 | $0.01879 |
| Opus 5.5 | $0.00086 | $0.00752 |
| Sonnet 5.5 | $0.00043 | $0.00376 |
| Haiku 4.5 | $0.00022 | $0.00188 |
Grade A, and why
akuko 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 today.
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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
akuko — story to film, one reviewed stage at a time
This file is a router. Each action lives in its own file under actions/; load it on demand and follow it. Do not inline action behaviour here. Shared rules live in lib/:
lib/state.md— the project file, stages, status transitions, decision folding. Read it before anything that writes.lib/hosts.md— host detection, what each host can do, the host adapter.lib/spend.md— the spend gate and cost ledger (WP-03).lib/providers.md— providers (WP-03).
The project format is schema/akuko-project.ts (akuko.json, JSON Schema in schema/akuko-project.schema.json).
Every action starts the same way
- Detect the host (
lib/hosts.md§Detection): A claude-artifact · B local · C ikenga. Runnode --experimental-strip-types hosts/detect.ts --tools <your FULL tool list — every loaded and deferred tool name>. If the output has awarning, or you are in any doubt, treat the host as A (artifact DB) and never create a project folder. Record the result inakuko.json.host. - Read the project through the host adapter (
readState()); if there is none, route tointake(orsetupif the person wants to configure first). - Fold decisions people made since the last run (
readDecisions()→lib/state.md§Decision folding) before doing anything else. - Load the action file and follow it. Write the project only through
writeState(); store files only throughstoreAsset().
Routing
| If the user says… | Load this | Owner |
|---|---|---|
| "set up akuko", "configure", "set a budget", "add my keys" | actions/setup.md |
WP-08 |
| "check my setup", "what's missing", "doctor" | actions/doctor.md |
WP-08 |
| "make a film from this story / script", "start a project", "intake" | actions/intake.md |
WP-04 |
| "break it down", "shot list", "breakdown" | actions/breakdown.md |
WP-04 |
| "characters", "locations", "look / style", "bible" | actions/bible.md |
WP-05 |
| "storyboard", "sketch board", "beat board", "board" | actions/board.md |
WP-21 |
| "key frames", "final panels", "keyframes" | actions/keyframes.md |
WP-22 |
| "animate", "make the clips", "motion" | actions/motion.md |
WP-10 · WP-11 |
| "voice-over", "music", "sound effects", "sound" | actions/sound.md |
WP-12 |
| "animatic", "rough cut", "assemble" | actions/assemble.md |
WP-13 · WP-15 |
| "render the film", "export the MP4", "export" | actions/export.md |
WP-15 · WP-17 |
| "I reviewed it", "apply my notes", "review" | actions/review.md |
WP-07a |
| "show me …", "open the board", "view" | actions/view.md |
WP-07c |
| "where are we", "what's next", "status" | actions/status.md |
— |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- actions/_frontmatter.ts 10 KB runs code
- actions/actions.test.ts 9.6 KB runs code
- actions/assemble.md 1.3 KB
- actions/bible.md 1.6 KB
- actions/board.md 1.4 KB
- actions/breakdown.md 6.6 KB
- actions/doctor.md 2.9 KB
- actions/export.md 1.4 KB
- actions/intake.md 5.8 KB
- actions/keyframes.md 1.5 KB
- actions/motion.md 1.5 KB
- actions/review.md 5.4 KB
- actions/setup.md 3.9 KB
- actions/sound.md 1.4 KB
- actions/status.md 2.3 KB
- actions/view.md 1.4 KB
- breakdown/__fixtures__/proposal-adapt.json 4.5 KB
- breakdown/__fixtures__/proposal-direct.json 3.4 KB
- breakdown/__fixtures__/screenplay.fountain 792 B
- breakdown/__fixtures__/story.md 675 B
- breakdown/apply.ts 14 KB runs code
- breakdown/breakdown.test.ts 22 KB runs code
- breakdown/cli.ts 6.6 KB runs code
- breakdown/fountain.ts 3.8 KB runs code
- breakdown/intake.ts 4.1 KB runs code
- breakdown/lint.ts 4.9 KB runs code
- breakdown/tags.ts 6.8 KB runs code
- decisions/__fixtures__/artifact-db-list.json 3.9 KB
- decisions/__fixtures__/conformed.json 281 B
- decisions/__fixtures__/decisions.jsonl 1.9 KB
- decisions/__fixtures__/iframe-state.txt 3.4 KB
- decisions/__fixtures__/ikenga-mirror.jsonl 819 B
- decisions/__fixtures__/the-beating.folded.json 23 KB
- decisions/artifact-db.ts 4.3 KB runs code
- decisions/can-approve.test.ts 4.2 KB runs code
- decisions/cli.test.ts 2.8 KB runs code
- decisions/cli.ts 6.2 KB runs code
- decisions/conformed.ts 4.0 KB runs code
- decisions/decision-schema.test.ts 2.8 KB runs code
- decisions/export-decision-schema.ts 1.9 KB runs code
- decisions/fold.test.ts 22 KB runs code
- decisions/fold.ts 26 KB runs code
- decisions/ikenga.ts 4.2 KB runs code
- decisions/jsonl.ts 4.9 KB runs code
- decisions/stores.test.ts 9.2 KB runs code
- fixtures/convert-fixture.ts 11 KB runs code
- fixtures/the-beating/akuko.json 18 KB
- fixtures/the-beating/board-fixture.json 13 KB
- hosts/claude-artifact.ts 6.6 KB runs code
- hosts/detect.ts 12 KB runs code
- hosts/hosts.test.ts 28 KB runs code
- hosts/ikenga.ts 2.8 KB runs code
- hosts/local.ts 5.4 KB runs code
- hosts/shared.ts 3.7 KB runs code
- hosts/types.ts 3.2 KB runs code
- lib/hosts.md 22 KB
- lib/providers.md 5.3 KB
- lib/spend.md 9.4 KB
- lib/state.md 12 KB
- LICENSE 11 KB
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.
- today First seen · 104 lines · 216 tokens per session scan A 5db70dae2e34
akuko is a skill published in the GitHub repository ikenga-hq/ikenga-pkgs (0 stars, last pushed today), licensed Apache-2.0. It adds 216 tokens to every session and 1,879 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-11-08.
akuko compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| akukoikenga-hq/ikenga-pkgs | Skill | 0 | today | Apache-2.0 | A | 216 | Claude Code |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |