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.
git clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/gosha70/code-copilot-team/hill)<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/hill"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/hill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/gosha70/code-copilot-team/hill"><img src="https://agentmods.dev/badge/commands/gosha70/code-copilot-team/hill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00000 | $0.00492 |
| Opus 5.5 | $0.00000 | $0.00197 |
| Sonnet 5.5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
hill 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 1mo 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
Update a scope's status on the hill chart of the active pitch.
Usage: /hill <scope> <up|down|done> [--force]
Steps
1. Parse arguments
<scope>— scope id (S1,S2, ...) as it appears inpitch.mdandhill.json.<up|down|done>— target status. Maps touphill,downhill,done.--force(optional) — required to move a scope fromdoneback touphill(treats the work as not-actually-done).
2. Find the active pitch
Scan specs/pitches/*/pitch.md for bet_status: building.
- 0 matches → refuse with: "No active cycle. Run
/cycle-start <pitch-id>first." -
1 match → refuse with: "More than one pitch is building (<list>). Resolve before running
/hill." - exactly 1 → that's the active pitch.
3. Verify scope and load hill.json
Read specs/pitches/<active-pitch>/hill.json. The named scope must exist. Refuse otherwise (likely a typo or the pitch was changed without re-running /cycle-start).
4. Validate the transition
| Current → Target | Allowed |
|---|---|
| uphill → downhill | yes |
| uphill → done | yes (skipping downhill is unusual but legal) |
| downhill → done | yes |
| downhill → uphill | yes (you discovered an unknown) |
| done → downhill | yes (work was prematurely declared done) |
| done → uphill | requires --force |
5. Update hill.json
- Set the scope's
statusto the target. - Set the scope's
last_updatedto ISO-8601 now. - Set the file root
updated_atto ISO-8601 now.
6. Report
Print:
- Pitch id, scope id and name
- Transition (e.g.
uphill → downhill) - Current state of all scopes (one-line summary like
S1=done S2=downhill S3=uphill) - If all scopes are
done: "All scopes complete. Run/cooldownto close the cycle."
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.
- 1mo ago First seen · 49 lines · 0 tokens per session scan A 2d1ea3f9ae72
hill is a command published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 492 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
portfolio
Show a read-only hub-wide portfolio of canonical Ideas and active Projects without duplicating topic-owned records.
story-continue
Resume an interrupted story from where you left off.
prp-prd
Interactive PRD generator - problem-first, hypothesis-driven product spec with back-and-forth questioning.
sdd
A command that creates three connected planning files for a software feature: requirements, design, and tasks.
project
Manage projects inside a topic wiki. Projects are folders under output/projects/ that group related outputs (playbooks, images, code, data) with a goal captured in WHY.md.
traceability-gen
A command that rebuilds a Markdown table linking requirements to project plans and tests. It reads requirement files, plan files, and test markers, then records what is planned or covered.