tracker

A command that records a completed piece of work in an execution log called audric-build-tracker.md. It adds a numbered entry at the top while preserving the file's format.

In plain words
What is it for?
Use it after committing or deploying a work slice to record what changed, why it changed, and any follow-up tasks requiring a person.
Why use it?
It keeps a reliable history of shipped work and prevents entries from being misnumbered or added before the work is actually completed.

Command for Claude Code

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/mission69b/t2000/tracker
Clone the repo
git clone --depth 1 https://github.com/mission69b/t2000

Made for: Claude Code.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 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 $0.00018 $0.00493
Opus 5 $0.00009 $0.00246
Sonnet 5 $0.00004 $0.00099
Haiku 4.5 $0.00002 $0.00049

Measured 2d ago against content hash 5fdb3ed3af00, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tracker 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.

.claude/commands/tracker.md · 49 lines

What it actually says

Log the slice just shipped to audric-build-tracker.md: $ARGUMENTS

What this file is

A reverse-chronological execution log — one S.N entry per shipped slice, newest at the top. It is the audit trail, NOT a forward backlog (that's HANDOFF_NEXT_AGENT.md). It's gitignored here — the real file lives in the private mission69b/t2000-internal repo, mounted at spec/.

Steps

  1. Read the top of audric-build-tracker.md to get the latest S.N. Increment it — never reuse or guess a number.
  2. Confirm the work is actually shipped (committed / deployed), not just written.
  3. Insert the new entry immediately below the **Rules:** block, above the current top entry.

Entry shape

Match the house style exactly — a heading, a one-line "why" with founder context where it exists, then bolded-lead bullets:

## S.<N> — <title> (<YYYY-MM-DD>)

<One or two lines: the driver / founder rationale / what forced this.>

- **<Category>:** what changed, concretely, with file or package names.
- **<Category>:** …
- **Founder ops owed (not in git):** anything requiring a human — DNS, Vercel
  project deletion, npm deprecate, dashboard changes. Omit if none.

Categories used in practice: Deleted · Kept · Added · Git · Docs/config · Redirects · SSOT · Archive · Rules · Held for founder nod · Founder ops owed.

Rules

  • Be specific. "Updated docs" is useless six months later; name the files.
  • Record what was NOT done and why — held decisions, deferred pieces, ops owed.
  • Don't editorialize the outcome. If something is partial or unverified, say so.
  • One entry per slice. Don't retro-edit older entries to look tidier.
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. 2d ago First seen · 49 lines · 18 tokens per session scan A 5fdb3ed3af00

Subscribe to this mod's changes

tracker is a command published in the GitHub repository mission69b/t2000 (23 stars, last pushed 2d ago), licensed MIT. It adds 18 tokens to every session and 493 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.