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/aksoftcode/aicrew/handoffgit clone --depth 1 https://github.com/AKSoftCode/aicrewWhat 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 | $0.00012 | $0.00501 |
| Opus 5 | $0.00006 | $0.00251 |
| Sonnet 5 | $0.00002 | $0.00100 |
| Haiku 4.5 | $0.00001 | $0.00050 |
Grade A, and why
handoff 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 yesterday.
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
Default output: caveman/lean — terse by default.
/normalor/lean offfor verbose. See~/Agents/agents/caveman.md.
/handoff
Overview
Switching tools mid-task (e.g. Claude → Cursor)? Three steps:
-
Early in your session, name it:
/session cursor my-taskThis sets the state file path:.ai/state/AI_STATE.cursor.my-task.md -
When ready to switch, run
/handoff. You get a compact block:HANDOFF: Target: cursor State file: .ai/state/AI_STATE.cursor.my-task.md Goal: Add rate limiting to /api/auth endpoint Current status: Phase 3 design confirmed — ready to implement Next step: Run TDD cycle for RateLimitMiddleware Tests: not run yet -
In the new tool, paste the block or just say:
Continue from .ai/state/AI_STATE.cursor.my-task.md
No chat replay. Each switch costs ~300 tokens instead of 15,000.
Generate a compact handoff package for switching tools/models without losing context.
Inputs
- Current session state file:
.ai/state/AI_STATE.<tool>.<session>.md
- Optional argument in
$ARGUMENTS(target tool or note)
If the state file does not exist, build a compact handoff from current session facts.
Output format
Return this exact structure in markdown:
HANDOFF:
Target:
- [target tool/model or "any"]
State file:
- [.ai/state/AI_STATE.<tool>.<session>.md or "not written yet"]
Goal:
- ...
Current status:
- ...
Key constraints:
- ...
Relevant files:
- ...
Latest errors/logs:
- ...
Next step:
- ...
Tests:
- ran / not run (+ short note)
Risks/assumptions:
- ...
Rules
- Keep it compact and copy/paste friendly.
- Preserve technical strings verbatim (commands, paths, errors).
- Do not invent facts. If unknown, write
unknown. - If writing tools are available, update state file before printing handoff.
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.
- yesterday First seen · 87 lines · 12 tokens per session scan A 9a3d6ccfead1
handoff is a command published in the GitHub repository AKSoftCode/aicrew (3 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 501 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 2026-08-31.
Other commands, from other repositories
implement
Execute implementation by processing atomic task files one at a time with Context Pinning (Atomic Traceability Model).
plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
clarify
Pre-plan interview — resolves spec ambiguity (v0.1 contract), pins the architectural lurkers from .specify/knowledge/architectural-lurkers.yaml, fires trigger-driven probes from .specify/knowledge/triggers.yaml, walks compliance scope, and writes decisions to specs/defaults/registry.yaml with provenance tagging.
cleanup
Detect and remove orphaned code, unused components, dead routes, and stale database artifacts.
registry
Discover, create, or update the Project Defaults Registry. Scans project manifests (package.json, pyproject.toml, Cargo.toml, go.mod, etc.), batches findings for HITL confirmation, then writes specs/defaults/registry.yaml with a full audit trail in changelog.md.
specify
Create or update the feature specification from a natural language feature description.