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/track-decisiongit 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/track-decision)<a href="https://agentmods.dev/commands/jonase47/ccpr/track-decision"><img src="https://agentmods.dev/badge/commands/jonase47/ccpr/track-decision.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 | $0.01546 |
| Opus 5 | $0.00000 | $0.00773 |
| Sonnet 5 | $0.00000 | $0.00309 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
track-decision 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/track-decision – Decide Lean vs. Full-Track (or reassess)
Interactive prerequisite check + Knockout check + Indicator score that determines whether a project runs in Lean-Track (prototype/PoC/spike, ~4 skills) or Full-Track (P0–P8, 109 skills).
Track-agnostic: runs at project start AND mid-flight as a re-assessment.
Argument: $ARGUMENTS = [optional: projectdir]
- Without argument: operates on
$(pwd). - With argument: operates on the given project directory.
Prerequisites
- If
docs/TRACK_DECISION.mdalready exists → re-assessment mode (new entry prepended, previous entries preserved). - If not → initial-decision mode.
Execution
1. Prerequisite Check (condition for Lean)
Ask interactively (each yes/no):
- Solo or mini-team (≤3 people)?
- Goal is to validate/learn/tech-spike — not to ship?
- Data: mock / test data / own demo data (no real persons)?
- Runs locally or on a non-public URL?
→ If all 4 = yes → proceed to Knockout check. → If at least 1 = no → Track = Full, skip to step 4.
2. Knockout Questions (1× yes = Full, non-negotiable)
| # | Question |
|---|---|
| K1 | Personal data (Art. 4 DSGVO) of real persons — including logs/analytics/test accounts? |
| K2 | Special data categories (Art. 9 DSGVO) — health, biometrics, religion, sexual orientation, trade union? |
| K3 | Production launch in <4 weeks, publicly or third-party accessible? |
| K4 | Regulatory scope applies? (BFSG/KRITIS/MDR/BaFin/sectoral — see clarification below) |
| K5 | External stakeholders with sign-off authority (client/principal with Gate expectations)? |
K4 clarified (1× yes = Full):
- BFSG (since 28.06.2025): B2C offering AND publicly/consumer-accessible AND in BFSG sector (online shops, banking, passenger transport, e-books, telecommunications, hardware computer systems, ATMs/ticketing/check-in). NOT relevant: B2B, internal tools, solo demos, closed pilot groups.
- KRITIS (energy, water, health, finance, transport, ICT, food, waste management, state & administration).
- MDR (medical device under Regulation (EU) 2017/745, including Software-as-Medical-Device).
- BaFin (banking, insurance, payment services, crypto custody).
- Other sectoral obligations (GwG, TKG, JuSchG/JMStV, ProdSG).
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 · 130 lines · 0 tokens per session scan A 76a685acc8f5
track-decision 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 1,546 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
loops
Weekly review — surface everything in-flight and force a ship / block / kill decision on each.
config
Configure team-management (non-secret settings) through a guided menu.
execute-phase
1. Read STATE.md — confirm phase [N] is in "planned" status.
plan-phase
Plan a phase of the project. Usage: /forge:plan-phase [N].
brd
Generate Business Requirements Document with stakeholder analysis. Usage: /mindforge:brd [project] [--stakeholders list].
mindforge:hire
Design technical interview process. Usage: /mindforge:hire [role] [--level junior|mid|senior|staff] [--type system-design|coding|behavioral].