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 agentmods add skills/grainulation/grainulator/initnpx skills add grainulation/grainulator --skill initgit clone --depth 1 https://github.com/grainulation/grainulatorWhat 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 | $0.00016 | $0.00394 |
| Opus 5 | $0.00008 | $0.00197 |
| Sonnet 5 | $0.00003 | $0.00079 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
init 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 2d 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.
What it actually says
/init -- Start a new research sprint
The user wants to start a new research sprint.
Arguments
$ARGUMENTS
Instructions
-
Parse the user's input to extract:
- Question: The core research question. If not explicit, ask.
- Audience: Who will consume the output (engineers, product, executives, etc.). Default to the repo context if detectable.
- Constraints: Any hard requirements or boundaries (semicolon-separated).
- Done criteria: What "done" looks like for this sprint.
-
Delegate to the canonical CLI init. Do NOT manually create claims.json or call wheat_add-claim. Run the full init via the Bash tool:
npx -y @grainulation/wheat init --headless \ --question "<question>" \ --audience "<audience>" \ --constraints "<constraint1>; <constraint2>" \ --done "<done criteria>"This creates all sprint files: claims.json, CLAUDE.md, AGENTS.md, .mcp.json, .gitignore, .claude/commands/wheat/, output directories, and the pre-commit hook. Using the CLI ensures the skill path and CLI path produce identical results.
-
After init completes, call
wheat_statusto verify the sprint was created successfully. -
Print a summary:
Sprint initialized: <slug> Question: <question> Audience: <audience> Claims: <count> Next steps: /research <topic> -- start gathering evidence /status -- view sprint dashboard
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.
- 2d ago First seen · 53 lines · 16 tokens per session scan A 3b3296fc73d2
init is a skill published in the GitHub repository grainulation/grainulator (87 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 394 once invoked, about $0.0001 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
project-sizing-guide
Software project effort estimation assistant. Outputs three-point estimates (optimistic/most-likely/pessimistic values with confidence intervals), T-shirt sizes, or Function Point Analysis (FPA) counts. Triggered when users ask 'how long will this feature take,' need to assess project workload, perform PERT…
sprint-wrap-up
End-of-sprint checklist — finalize results, clean up worktrees, update docs, prepare for retro. Any agent can run this.
session-wrapup
End-of-session checkpoint — append diary, update active sprint doc with interim results/retro, write tech-lead handoff, commit and push. Use before /compact or at end-of-day. Distinct from sprint-wrap-up which closes a sprint.
shutdown-dev
Cleanly shut down a dev teammate — instruct them to write a context summary to plan/agent-context/{name}.md first, receive their approval, verify process exit. Use for scale-down, rotation, sprint wrap-up.
sprint-planning
Collaborative sprint planning — validate issues, prioritize, get architect/SM input, create task queue. Any agent can facilitate.
sprint-retrospective
Run a sprint retrospective — gather data, analyze incidents, propose action items. Any agent can facilitate.