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/jonase47/ccpr/release-baselinegit clone --depth 1 https://github.com/jonase47/ccprWrote 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/jonase47/ccpr/release-baseline)<a href="https://agentmods.dev/commands/jonase47/ccpr/release-baseline"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/release-baseline.svg" alt="Measured on agentmods" 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 | $0.01232 |
| Opus 5 | $0.00000 | $0.00616 |
| Sonnet 5 | $0.00000 | $0.00246 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
release-baseline 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release-baseline – Set project state as baseline
Makes a "cut" after a release: project state is documented as given, HANDOVER is archived and summarized, docs are split into Frozen/Active.
Argument: $ARGUMENTS = [Release version, e.g. "v1.0.0"]
Prerequisites
- Gate-P7 Go or explicit user request
Execution
1. Read prep report
Read docs/.baseline-prep.md (created via baseline.sh).
If not present or older than 10 min: inform the user that
~/.claude/scripts/baseline.sh [version] [projectdir] should be run first.
2. Create BASELINE.md
Create docs/BASELINE.md:
# Baseline: [Version]
**Release**: [Version]
**Date**: [DD.MM.YYYY]
**Status**: [e.g. MVP completed, all gates P0-P7 passed]
## Project State Summary
[Take HANDOVER summary from prep report. If not available: summarize from HANDOVER.md yourself (max. 10 sentences)]
## Core Architecture
[3-5 sentences from docs/architecture/ARCHITECTURE.md – architecture style, main components, deployment model]
## Tech Stack
[Bullet points from .claude/CLAUDE.md or docs/architecture/TECH_STACK.md]
## Completed Milestones
[Table from docs/planning/PROJECT_PLAN.md – completed milestones only]
## Important Decisions
[Take from .claude/CLAUDE.md "Important Decisions" table]
3. Update project CLAUDE.md
Add a "Baseline" section after "Current Phase" (before "Project goals"):
## Baseline
**Release**: [Version] ([Date])
**Status**: [e.g. MVP completed, all gates P0-P7 passed]
### Frozen Docs (read only when needed)
- docs/discovery/ (P0)
- docs/concept/ (P1)
- docs/validation/ (P2)
- docs/architecture/ (P3)
- docs/planning/PROJECT_PLAN.md (milestones)
### Active Docs (at every session start)
- docs/HANDOVER.md (Handover)
- docs/BASELINE.md (reference)
- docs/planning/BACKLOG.md (current work)
- docs/planning/SPRINT.md (current sprint)
If a Baseline section already exists: update it (version, date, status).
4. Reset HANDOVER.md
Before creating the fresh file, scan the current docs/HANDOVER.md for inbox entries: lines
matching commands/cleanup.md §1's marker pattern (grep -c '^- INBOX [|]' docs/HANDOVER.md).
baseline.sh already copies the whole file into the archive (see prep report), so this step is not
the rescue — it is what keeps an untriaged finding in the triage loop instead of letting it go
quiet inside the archive: a release cut is not a triage decision and must not silently drop the
finding on the reader's behalf. A blocking guard would not help here either (the file is archived
either way, and a guard that holds up a release just gets bypassed) — carry the entries forward
instead.
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 · 120 lines · 0 tokens per session scan A c33cabda90ad
release-baseline is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,232 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 2026-09-03.
Other commands, from other repositories
complete-milestone
Archive a completed milestone, generate a release report, and prepare the next.
gsd:complete-milestone
Archive completed milestone and prepare for next version.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary — the complete landing pipeline.
update-check.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
update-smart.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
parallel
You are executing the /hydra:parallel command. Start multiple agents simultaneously in different worktrees.