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/developerz-ai/ai-task-master/configgit clone --depth 1 https://github.com/developerz-ai/ai-task-masterWhat 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 | $0.00000 | $0.00471 |
| Opus 5 | $0.00000 | $0.00235 |
| Sonnet 5 | $0.00000 | $0.00094 |
| Haiku 4.5 | $0.00000 | $0.00047 |
Grade A, and why
config 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.
What it actually says
aitm config
Read and write the JSON config files.
Two surfaces, same shape (see ../config.md):
| Scope | File | Selector |
|---|---|---|
| Global | ~/.aitm.json |
default |
| Project | ./.ai-task-master/config.json |
--project |
Signature
aitm config set <key> <value> [--project]
aitm config unset <key> [--project]
aitm config get <key> [--project]
aitm config list [--project]
<key> is dotted: models.smart, mergeMethod, autoMerge, concurrency. <value> is JSON-parsed ("sk-or-...", true, 5, null).
Capability tiers
Models are configured by capability, not by subagent role. Tiers and their canonical defaults (OpenRouter routes — see ../auth.md):
| Tier | Default | Used by |
|---|---|---|
fast |
anthropic/claude-haiku-4.5 |
Orchestrator routing, toModelOutput compaction |
generic |
anthropic/claude-sonnet-4.6 |
Fallback for any unspecified tier |
smart |
anthropic/claude-opus-4.7 |
Planner, Reviewer |
coding |
anthropic/claude-opus-4.7 |
Worker |
Role→tier mapping is fixed (src/credentials/credentials.ts §ROLE_CAPABILITY); tier→model is user-configurable.
API key
aitm config set openrouterApiKey "sk-or-..." writes the key. aitm start still falls back to OPENROUTER_API_KEY in env (see ../auth.md §"LLM provider" — resolution order).
SRP
ConfigWriter is the only module allowed to mutate config files. Writes are atomic (temp file + rename) and validated against ConfigFileSchema before persisting.
See also
../config.md../auth.md./start.md
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 · 49 lines · 0 tokens per session scan A 3f1c717db3ad
config is a command published in the GitHub repository developerz-ai/ai-task-master (5 stars, last pushed 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 471 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.
Other commands, from other repositories
upgrade-webkit
Upgrade Bun's WebKit fork to the latest upstream version of WebKit.
dedupe
Find duplicate GitHub issues.
ashlr-dashboard
Rich token-savings dashboard — per-tool bar charts, 7d/30d sparklines, projected annual savings, and cost in dollars.
scriptwriter-draw
Draw a random chaos card from the 13-card deck — a plot-twist prompt the user can use as a scene seed, a basistext for an RRR cascade, or a riff for a room contribution.
specsync-create-spec
Create a new spec-sync module spec.
nimbus-embedding-routing
Hybrid 384/1536-dim embedding routing (Phase 5 T6 PR 3): PROSEHEAVYTYPES, EMBEDDINGDIMLOCAL/EMBEDDINGDIMOPENAI, the RoutingEmbeddingPipeline wrapper, dual-table search (vecitems384 + vecitems1536 via vectorSearchChunksDual), the V30 migration (1536-dim table + dim-aware delete triggers), the nimbus index reembed CLI +…