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 cnfjlhj/ai-collab-playbook --skill research-lead-sidecargit clone --depth 1 https://github.com/cnfjlhj/ai-collab-playbookWrote 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/cnfjlhj/ai-collab-playbook/research-lead-sidecar)<a href="https://agentmods.dev/skills/cnfjlhj/ai-collab-playbook/research-lead-sidecar"><img src="https://agentmods.dev/badge/skills/cnfjlhj/ai-collab-playbook/research-lead-sidecar/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/cnfjlhj/ai-collab-playbook/research-lead-sidecar"><img src="https://agentmods.dev/badge/skills/cnfjlhj/ai-collab-playbook/research-lead-sidecar.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 | $0.00061 | $0.00329 |
| Opus 5 | $0.00030 | $0.00164 |
| Sonnet 5 | $0.00012 | $0.00066 |
| Haiku 4.5 | $0.00006 | $0.00033 |
Grade A, and why
research-lead-sidecar 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 13d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
9 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.
- agents/openai.yaml 331 B
- assets/findings.md.tpl 346 B
- assets/progress.md.tpl 288 B
- assets/research-state.yaml.tpl 469 B
- references/dispatch-prompts.md 2.1 KB
- references/role-routing.md 2.6 KB
- references/worker-handoff-template.md 758 B
- references/workspace-files.md 1.6 KB
- scripts/init_workspace.py 3.3 KB runs code
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.
- 13d ago First seen · 33 lines · 61 tokens per session scan A 5c67dfb783fd
research-lead-sidecar is a skill published in the GitHub repository cnfjlhj/ai-collab-playbook (443 stars, last pushed 2mo ago), with no licence file. It adds 61 tokens to every session and 329 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 2026-08-30.
Other skills, from other repositories
vibe-ui-design
A process for defining a consistent user-interface design system, covering colors, fonts, spacing, shapes, shadows, animations, and reusable components.
vibe-ui-beautify
A workflow for adding motion and touch feedback to interface components, such as transitions, animations, and 3D effects.
vibe-security
A defensive security review workflow for code, dependencies, and application configuration. It checks for vulnerabilities such as unsafe input handling, unauthorized access, exposed sensitive data, and known problems in installed packages.
vibe-autopilot
Use this skill when the user requests fully autonomous, 24/7 hands-free development without human intervention.
vibe-plan
Use this skill to create a phased development plan based on requirements, architecture, and API docs.
vibe-test
A testing workflow that follows TDD, or test-driven development: write a test that fails, add the smallest code needed to pass it, then clean up the code. It produces tests and a test report.