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.
git clone --depth 1 https://github.com/thixpin/pitwayWrote 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/commands/thixpin/pitway/task-discard)<a href="https://agentmods.dev/commands/thixpin/pitway/task-discard"><img src="https://agentmods.dev/badge/commands/thixpin/pitway/task-discard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/thixpin/pitway/task-discard"><img src="https://agentmods.dev/badge/commands/thixpin/pitway/task-discard.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.00278 |
| Opus 5.5 | $0.00000 | $0.00111 |
| Sonnet 5.5 | $0.00000 | $0.00056 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
task-discard 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 1mo 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-discard
Role: Orchestrator
pitway task-discard <id> --reason <text> [--json]
Abandons one dispatched task's worktree without integrating — the single
sanctioned exit besides task-integrate for a live dispatch. Requires an
explicit --reason <text>. Appends a worktree_discard journal record
(reason + discarded branch HEAD SHA when still resolvable, evidence-only),
removes the worktree and scaffolding branch (tolerating an
already-vanished worktree), and transitions the task in_progress → failed through the existing state machine — whence failed → ready
allows a fresh dispatch, with attempts accumulating.
Discarded work is unrecoverable through PitWay. Never discard in an
integrate crash window (cleanup pending, or an applied-but-unrecorded
diff): the work is already recorded or applied in the main tree —
re-running task-integrate <id> finishes it. pitway resume names those
states read-only.
See ../protocol-driver.md (Parallel dispatch). Run pitway task-discard --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.
- 1mo ago First seen · 31 lines · 0 tokens per session scan A 79da77dbeb8d
task-discard is a command published in the GitHub repository thixpin/pitway (20 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 278 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 2026-08-30.
Other commands, from other repositories
implement
Execute all implementation tasks from tasks.md with test-driven development, parallel batching, and atomic commits.
gjalla-attest
Create a commit attestation for your changes.
gjalla-log
Show recent semantic change history.
implement-feature
Implement an approved feature plan with fresh-context slices, TDD, revision-bound evidence, and PR-ready output.
gate
Dispatch the moai workflow gate with: $ARGUMENTS.
ticket
Take a GitHub issue through an isolated implementation and pull request in its own Herdr tab.