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 researchgit 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/research)<a href="https://agentmods.dev/skills/ikenga-hq/ikenga-pkgs/research"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/research/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/research"><img src="https://agentmods.dev/badge/skills/ikenga-hq/ikenga-pkgs/research.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 | $0.00196 | $0.01315 |
| Opus 5.5 | $0.00078 | $0.00526 |
| Sonnet 5.5 | $0.00039 | $0.00263 |
| Haiku 4.5 | $0.00020 | $0.00131 |
Grade A, and why
research 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 2mo 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
research — dispatch-only research pipeline surface
This file is a router. Each action lives in its own file under actions/;
load on demand. The state contract (which ikenga.db tables are touched,
read-vs-write boundary, dispatch-only scope) is in lib/state.md — read it
before building any action.
skill-core note:
depends_on: ['skill-core']is declared above.skill-coreships ascom.ikenga.skill-coreonikenga-pkgsmain. Per the G-04 contract and the lint spec in06-skill-action-contract.md§5, no other target is legal.
Pipeline-stages convention: This skill extends the R-04 Pipeline-stages convention to the research domain.
research-sweepproposals carryux_modeper the §Pipeline-stages mapping —silentfor intra-stage agent moves,confirmfor operator one-offs,approvefor any outward dispatch (hand-to-sales, source re-scrape trigger) or any terminal-crossing action. The research stage enum is:draft → review → validated(terminal:archived). See06-skill-action-contract.md§Pipeline-stages.
R-03 (Query-collapse): No query actions are present. Domain skills are permanently dispatch-only. Interactive questions route through
skill-query.
Purpose (one line)
Surface next-action proposals for monitored sources (stale refresh) and open
research notes (stage-advance, dossier commission, hand-to-sales) — reading
ikenga.db state, never owning CRUD.
Dispatch actions
| Action | File | Mode | One-liner |
|---|---|---|---|
setup |
actions/setup.md |
streaming |
Configure the research pipeline: monitored sources, cadences, default depth, owner. Writes .atelier/skill-research/manifest.json. |
research-sweep |
actions/research-sweep.md |
approve |
Read open research notes + monitored sources, produce stale-refresh and dossier-advance proposals with evidence; pause for operator approval. |
draft-report |
actions/draft-report.md |
confirm |
Draft a new research report or dossier in dock chat (D-02 setup-in-chat pattern); pane/host path writes the row. |
What ships with it
4 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.
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.
- 2mo ago First seen · 101 lines · 196 tokens per session scan A e73107a4fed4
research is a skill published in the GitHub repository ikenga-hq/ikenga-pkgs (0 stars, last pushed today), licensed Apache-2.0. It adds 196 tokens to every session and 1,315 once invoked, about $0.0008 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 2026-08-31.
research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| researchikenga-hq/ikenga-pkgs | Skill | 0 | today | Apache-2.0 | A | 196 | 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 | 314k | 5d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |