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 commands/waniwani-ai/sdk/implementgit clone --depth 1 https://github.com/WaniWani-AI/sdkWhat 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 | $0.00013 | $0.00681 |
| Opus 5 | $0.00006 | $0.00341 |
| Sonnet 5 | $0.00003 | $0.00136 |
| Haiku 4.5 | $0.00001 | $0.00068 |
Grade A, and why
implement 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 3d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start implementing the Linear ticket specified in $ARGUMENTS.
Steps
-
Fetch the Linear ticket using
mcp__linear__get_issuewith the ticket ID from $ARGUMENTS (e.g., "WAN-123")- If the ticket doesn't exist, inform the user and stop
-
Get the current git user using
git config user.nameto determine the branch prefix- Convert to lowercase and replace spaces with hyphens (e.g., "John Doe" → "john-doe")
-
Create and checkout a new branch with the naming convention:
{user}/{linear_ticket_id}- Example:
maxime/WAN-123 - Use:
git checkout -b {user}/{ticket_id} - If the branch already exists, check it out instead:
git checkout {user}/{ticket_id}
- Example:
-
Mark the ticket as "In Progress" using
mcp__linear__update_issue:- Set the state to "In Progress"
- This signals to the team that work has started on this ticket
-
Display ticket information to the user:
- Title
- Description
- Status
- Priority
- Any linked issues or parent tickets
-
Enter plan mode using the EnterPlanMode tool to start planning the implementation:
- The plan should be based on the ticket description and acceptance criteria
- Consider the project's architecture and coding standards (from CLAUDE.md)
- Break down the work into concrete implementation steps
Branch Naming
- Format:
{git_username}/{LINEAR_TICKET_ID} - Git username: lowercase, spaces replaced with hyphens
- Ticket ID: uppercase (e.g., WAN-123)
Examples:
- User "maxime", ticket "WAN-456" →
maxime/WAN-456 - User "John Doe", ticket "wan-789" →
john-doe/WAN-789
Planning Guidelines
When entering plan mode, focus on:
- Understanding the scope - What exactly needs to be built?
- Identifying affected files - Which files need to be created or modified?
- Dependencies - What needs to happen first? (schema → types → API → UI)
- Testing approach - How will the implementation be verified?
- Edge cases - What could go wrong?
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.
- 3d ago First seen · 81 lines · 13 tokens per session scan A 7bd0ef2cb516
implement is a command published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed 5d ago), licensed MIT. It adds 13 tokens to every session and 681 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 commands, from other repositories
onplana-connect
Connect Claude Code to the Onplana MCP server, then verify it works.
flow-nexus-neural
Train and deploy neural networks in distributed sandboxes.
session-start
Invoke at the BEGINNING of every working session. Token budget: 500–1,500. -->.
build-concierge-router
Guides you through building a complete Concierge web-form router from scratch — teams, meeting types, rules, distributions, and the live router — with a confirmation checkpoint before anything is created.
audit-routing
Audit all Chili Piper concierge routers for coverage gaps, stale rules, empty distributions, and catch-all overflow.
release-manager
Automated release coordination and deployment with ruv-swarm orchestration for seamless version management, testing, and deployment across multiple packages.