track

A set of project-tracking commands that helps choose and manage either a lightweight path for prototypes or a fuller path for larger work.

In plain words
What is it for?
Use it to choose or reassess a project track, create project rules and planning files, record what was learned, and decide whether a prototype should continue, change direction, or stop.
Why use it?
It reduces uncertainty about which process to follow and keeps key project decisions, plans, and lessons recorded in shared documents.

Command

Install

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.

agentmods
npx agentmods add commands/jonase47/ccpr/track
Clone the repo
git clone --depth 1 https://github.com/jonase47/ccpr
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 465 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00465
Opus 5 $0.00000 $0.00233
Sonnet 5 $0.00000 $0.00093
Haiku 4.5 $0.00000 $0.00047

Measured yesterday against content hash f342a8699e38, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

track 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.

Manual/commands/track.md · 20 lines

What it actually says

Track Skills (cross-cutting, 6 commands)

Entry-point and cross-cutting commands. /track-decision runs first; the others compose Lean-Track / Full-Track / consistency checks.

Command Title Description
/track-decision Decide Lean vs. Full-Track (or reassess) Prerequisite check + Knockout (K1–K5) + Indicator score (I1–I5). Determines Lean (prototype/PoC/spike) or Full (P0–P8). Also for mid-flight reassessment. No downgrade Full → Lean.
/constitution Create or revise the project Constitution Creates docs/CONSTITUTION.md with Inviolable/Default/Aspirational. Hybrid mode: greenfield with domain bootstrap, existing Full-Track reads phase docs, Lean precursor reads FRAME. Read as mandatory input by all gates.
/lean-frame Create Lean-Track Single-Source-of-Truth Creates docs/FRAME.md (max. 5 KB, 8 sections) + docs/CLAUDE-lean.md. Replaces the P0+P1+P3 conception work for prototypes.
/lean-learn Validate Lean-Track and make a decision Creates docs/LEARNINGS.md with hypothesis check and decision PROMOTE/PIVOT-soft/PIVOT-hard/DROP. On pivot: module table (keep/refactor/rebuild).
/lean-promote Promote Lean → Full-Track via Promotion Brief Creates docs/PROMOTION_BRIEF.md (7 sections) as bootstrap input for /project-init. Archives FRAME/LEARNINGS/CLAUDE-lean to docs/lean-archive/.
/cross-check Cross-Artifact Consistency Check Across Phases Checks inconsistencies across phases (features ↔ auth, NFR ↔ tests, ADRs ↔ Constitution, …). 7 rules initially, growing iteratively. Recommended before gates.
Changes

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.

  1. yesterday First seen · 20 lines · 0 tokens per session scan A f342a8699e38

Subscribe to this mod's changes

track 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 465 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.