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/gosha70/code-copilot-team/cycle-startgit clone --depth 1 https://github.com/gosha70/code-copilot-teamWhat 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 | $0.00000 | $0.00554 |
| Opus 5 | $0.00000 | $0.00277 |
| Sonnet 5 | $0.00000 | $0.00111 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
cycle-start 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
Begin a cycle for a bet pitch — initializes the hill chart and transitions the pitch to building.
Usage: /cycle-start <pitch-id>
Steps
1. Parse arguments
<pitch-id> is the directory name under specs/pitches/. If absent, list pitches with bet_status: bet and ask.
2. Verify state
Read specs/pitches/<pitch-id>/pitch.md. Required:
bet_status: bet. Refuse if any other status.cycle:non-empty.
Run bash ~/.claude/templates/sdd/validate-pitch.sh --pitch-id <pitch-id>. Refuse on validator failure.
3. Parse scopes
From pitch.md, extract every ### S<N>: <name> heading under the ## Scopes section. Build the scope list as [{id: "S1", name: "..."}, ...].
Refuse if fewer than 3 or more than 7 scopes are found — that's a malformed pitch.
4. Generate hill.json
Write specs/pitches/<pitch-id>/hill.json matching the schema in ~/.claude/templates/sdd/hill-chart.json:
{
"pitch_id": "<pitch-id>",
"cycle": "<NN>",
"updated_at": "<ISO-8601 now>",
"scopes": [
{
"id": "S1",
"name": "<scope name from pitch.md>",
"status": "uphill",
"last_updated": "<ISO-8601 now>"
}
]
}
All scopes start at uphill. Refuse to overwrite an existing hill.json — that means the cycle was already started; the user should /hill to update existing scopes, not re-init.
5. Update pitch frontmatter
In pitch.md:
bet_status:frombet→building
6. Append to bet log
Add a row: | <YYYY-MM-DD> | building | Cycle NN started; hill chart initialized. |
7. Re-validate
bash ~/.claude/templates/sdd/validate-pitch.sh --pitch-id <pitch-id>. Refuse if it fails — restore prior state.
8. Report
Print:
- Pitch id, title, cycle number
- Number of scopes initialized to
uphill - Path to the new
hill.json - Next step: "Use the
scope-executoragent on a scope to begin work, or/hill <scope> downto mark a scope mechanical."
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 · 67 lines · 0 tokens per session scan A a3283bb54ac2
cycle-start is a command published in the GitHub repository gosha70/code-copilot-team (6 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 554 tokens. 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
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.