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-addgit 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 | $0.00014 | $0.00373 |
| Opus 5 | $0.00007 | $0.00187 |
| Sonnet 5 | $0.00003 | $0.00075 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
task-add 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-add
Role: Main Agent
pitway task-add <milestone-id> --file <path> --change-log <text> [--json]
Use to insert one new task into a confirmed or in_progress milestone —
corrective or follow-on work discovered mid-flight that belongs alongside
the existing task graph, not a new milestone. Requires --file (one task
definition — the next sequential Tnnn id, a name, and every other
taskSchema field except execution-only ones, which are derived) and
--change-log (why); running the command is itself the approval. Refuses
on draft (use milestone-add --replace), review (resolve verification
first), completed, or cancelled, and on any depends_on id that is
unknown or cancelled.
Dispatch rule: the addition is a pending journal amendment until the
next checkpoint commit. Inline task-update <new-id> in_progress works
immediately; task-dispatch on any task refuses until a checkpoint (e.g. a
sibling task's completion commit) folds the pending entry.
Task file format: ../draft-formats.md.
See ../protocol-driver.md. Scope entries (write_scope, context_files, relevant_files) must name
files, never directories -- Core matches dirty paths exactly, so a directory
entry can never be satisfied at execution; the command refuses it by name
(M045). Files that do not exist yet are fine.
Run pitway task-add --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 · 37 lines · 0 tokens per session scan A 579e4389c37b
task-add is a command published in the GitHub repository thixpin/pitway (19 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 373 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）.
conventions-check
Check AGENTS.md, CLAUDE.md, and the projected agent artifacts (skills, subagents, commands) against the repo's conventions.
resume
恢复本 session 的 PACEflow（删除 pause 标志）.
qux
Reference command fixture for the core pack.