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 skills/mitodl/agent-kit/witan-project-trackernpx skills add mitodl/agent-kit --skill witan-project-trackergit clone --depth 1 https://github.com/mitodl/agent-kitWrote 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/skills/mitodl/agent-kit/witan-project-tracker)<a href="https://agentmods.dev/skills/mitodl/agent-kit/witan-project-tracker"><img src="https://agentmods.dev/badge/skills/mitodl/agent-kit/witan-project-tracker.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 | $0.00128 | $0.02246 |
| Opus 5 | $0.00064 | $0.01123 |
| Sonnet 5 | $0.00026 | $0.00449 |
| Haiku 4.5 | $0.00013 | $0.00225 |
Grade A, and why
witan-project-tracker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Tracker
Tracks engineering work across sessions from discovery through delivery. Each
project is a WorkflowProject node in the witan graph. Each agent
session contributes a WorkflowSession. When a project completes, a
WorkflowTrace is assembled for the corpus.
The context-injection hook (Claude Code) / extension (Pi) auto-injects active project context into every session in the repo, so you rarely need to find a project slug manually.
Starting a Session: Joining an Existing Project
When the hook injects context showing an active project that matches your work:
workflow_session_start(
project_slug="wp-add-vault-k8s-auth-a3f912",
session_id="<$CLAUDE_SESSION_ID on Claude Code, or any stable session UUID>",
phase="implementation",
)
Link the session before doing substantive work. The phase should reflect what this particular session will focus on, not necessarily the project's current overall phase.
Hold on to the session_slug in the returned handle. Pass it to memory_store
and workflow_trace_mine so what you record this session is attributed to it, and
to workflow_session_end when you close. The protocol carries no session state,
so the handle is the only link between these calls.
Starting a Session: Creating a New Project
If no active project in the injected context matches the work:
workflow_project_create(
title="Add Vault K8s auth to ol-django",
description="Wire Vault K8s auth using hvac for secret injection at runtime. Driven by compliance requirement to stop using static env secrets.",
phase="discovery",
github_issue="github.com/mitodl/ol-django/issues/847",
tags=["vault", "kubernetes", "secrets"],
)
Then immediately start a session:
workflow_session_start(
project_slug="<slug returned above>",
session_id="<session UUID>",
phase="discovery",
)
The call is re-entrant: if it returns existed: true, a session for this
(project_slug, session_id) was already open and you've been handed that same
handle back — safe to retry after a transport error without duplicating the
session. Any newly-supplied repo and tags are merged in; phase stays at what the
first call set. Once a session has been ended, the same session_id starts a
fresh one, so several working stints under one Claude Code session each get
their own record.
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.
- 3d ago First seen · 258 lines · 128 tokens per session scan A c8e5a2c721d6
witan-project-tracker is a skill published in the GitHub repository mitodl/agent-kit (2 stars, last pushed today), licensed BSD-3-Clause. It adds 128 tokens to every session and 2,246 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…