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/thixpin/pitway/task-updategit clone --depth 1 https://github.com/thixpin/pitwayWhat 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 | $0.00015 | $0.00520 |
| Opus 5 | $0.00008 | $0.00260 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
task-update 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
task-update
Role: Orchestrator
pitway task-update <id> <status> [--result <path>] [--message <path>] [--usage <json>] [--evidence <id>] [--json]
The only way a task's status ever changes, and the only way its completion
commit ever gets made. You run this — a dispatched worker never does; it
reports back to you instead (see ../protocol-worker.md).
Typical calls: in_progress to start a task (the tree must be clean apart
from the task's own declared scope, tasks.yaml, verification state, and
pending journal targets — see ../coordination.md), review once a worker reports done, completed --result <file> --message <file> to persist the worker's report and
commit its files atomically, blocked/failed when a worker couldn't
proceed. --result's summary/evidence are capped on the way in — see
../report-format.md.
in_progress is also a legal recovery transition from review — for a
task stuck there because completed couldn't resolve any valid
task-verify evidence. Unlike the fresh-start case, this tolerates the
task's own already-dirty write_scope/relevant_files paths (carried over
uncommitted from the original attempt); any other unrelated dirty path
still refuses. The same applies to failed/blocked → ready → in_progress
retries. See ../task-verify.md.
--usage <json> accumulates measured token usage onto the task — a MUST
when completing a dispatched worker's task and its tool result reported
usage (../dispatch.md step 8, ../protocol-driver.md "Dispatch
discipline"); never estimated or supplied for inline work with no runtime
figure available.
Result/usage payload shapes: ../draft-formats.md.
--driver / --model : runtime-reported traceability stored in PitWay evidence (tasks.yaml, task-status --json); never added to Git trailers.
See ../protocol-driver.md and ../dispatch.md. Run
pitway task-update --help for flags.
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 · 46 lines · 0 tokens per session scan A a1bb81a327a5
task-update is a command published in the GitHub repository thixpin/pitway (19 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 520 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.
Other commands, from other repositories
pause
仅本 session 暂停 PACEflow 流程门（session 结束自动失效，artifact 保护保留）.
disable
在当前项目停用 PACEflow（不删除任何 artifact，随时可恢复）.
enable
在当前项目启用 PACEflow（首次启用会引导选择 artifact 存放位置）.
resume
恢复本 session 的 PACEflow（删除 pause 标志）.
conventions-check
Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.
qux
Reference command fixture for the core pack.