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/madappgang/claude-code/create-taskgit clone --depth 1 https://github.com/MadAppGang/claude-codeWhat 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 | $0.00019 | $0.01434 |
| Opus 5 | $0.00010 | $0.00717 |
| Sonnet 5 | $0.00004 | $0.00287 |
| Haiku 4.5 | $0.00002 | $0.00143 |
Grade A, and why
autopilot-create-task 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.
How it starts
The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<user_request> $ARGUMENTS </user_request>
<phase number="2" name="Classify and Tag">
<steps>
<step>
Classify task type:
- BUG_FIX: Fix/bug/error/crash patterns
- FEATURE: Add/implement/create/new patterns
- REFACTOR: Refactor/clean/optimize patterns
- UI_CHANGE: UI/design/component/style patterns
- TEST: Test/coverage/e2e patterns
- DOCUMENTATION: Doc/readme patterns
</step>
<step>
Select appropriate tag(s):
- @frontend - Frontend implementation
- @backend - Backend implementation
- @debug - Bug investigation
- @test - Test creation
- @review - Code review + PR
- @refactor - Code improvement
- @research - Investigation
- @ui - UI validation
</step>
<step>
If unclear, ask user (AskUserQuestion):
"Please select the appropriate tag for this task:
1. @frontend (React/Vue implementation)
2. @backend (API/database work)
3. @debug (Bug fixing)
4. @test (Test creation)
5. @ui (Design/visual work)"
</step>
</steps>
</phase>
<phase number="3" name="Generate Acceptance Criteria">
<steps>
<step>
Generate acceptance criteria based on task type:
For FEATURE:
- Functional requirements (what it must do)
- User-visible behavior
- Edge cases to handle
For BUG_FIX:
- Steps to reproduce (before)
- Expected behavior (after)
- Regression test requirement
For UI_CHANGE:
- Visual requirements
- Responsive behavior
- Accessibility requirements
</step>
<step>
Present criteria to user for validation (AskUserQuestion):
"Generated acceptance criteria:
1. [criterion 1]
2. [criterion 2]
3. [criterion 3]
Approve? (Yes / Modify / Add more)"
</step>
</steps>
</phase>
<phase number="4" name="Create Linear Issue">
<steps>
<step>
Read Linear configuration from .claude/autopilot.local.md
(team ID, project ID, labels)
</step>
<step>
Create issue via Linear API:
```bash
# Using Linear SDK through helper script
bun run ${CLAUDE_PLUGIN_ROOT}/scripts/linear-client.ts create-issue \
--title "$TITLE" \
--description "$DESCRIPTION" \
--team "$TEAM_ID" \
--labels "$LABELS" \
--assignee "$AUTOPILOT_BOT_USER_ID"
```
</step>
<step>
Add @autopilot label to trigger pickup
</step>
</steps>
</phase>
<phase number="5" name="Confirm">
<steps>
<step>
Present confirmation:
"Task created successfully:
**Title**: {title}
**ID**: {issue_id}
**Tags**: {tags}
**Status**: Assigned to autopilot
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 · 208 lines · 19 tokens per session scan A 0e37dd5459dd
autopilot-create-task is a command published in the GitHub repository MadAppGang/claude-code (279 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 1,434 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.