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/backlog)<a href="https://agentmods.dev/commands/thixpin/pitway/backlog"><img src="https://agentmods.dev/badge/commands/thixpin/pitway/backlog/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/backlog"><img src="https://agentmods.dev/badge/commands/thixpin/pitway/backlog.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 | $0.00814 |
| Opus 5.5 | $0.00000 | $0.00326 |
| Sonnet 5.5 | $0.00000 | $0.00163 |
| Haiku 4.5 | $0.00000 | $0.00081 |
Grade A, and why
backlog 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
backlog
Role: Orchestrator (add, promote, archive) · either (list, show)
pitway backlog add --title <text> --reason <text> [--milestone <id>] [--task <id>] [--json]
pitway backlog list [--status pending|promoted|archived] [--milestone <id>] [--task <id>] [--json]
pitway backlog show <id> [--json]
pitway backlog promote <id> --task <id> [--milestone <id>] [--json]
pitway backlog archive <id> --reason <text> [--json]
Use when you discover work that is genuinely out of scope for the current
task or milestone and want to continue without expanding it — capture it,
keep going, deal with it later. backlog add works with no active
milestone — it records source.milestone: null in that case, no
milestone required. backlog promote still requires an active/resolvable
milestone, since it targets a task, which is inherently milestone-scoped;
only add's milestone coupling was removed.
backlog add --title <text> --reason <text> [--milestone <id>] [--task <id>]— records apendingitem.--milestone/--taskhere are source annotation only (defaults to the active milestone — ornullwhen none is active — and no task, when omitted) — they never control where the mutation's journal entry attaches (when a milestone is active, that is always the active milestone, unconditionally, with no override:.pitway/backlog.yamlis a shared file, not owned by any one milestone's directory, so letting a flag redirect attachment could misattribute a pending entry to a milestone that will never checkpoint it). With no active milestone, behavior is otherwise unchanged.backlog list [--status pending|promoted|archived]andbacklog show <id>— read-only.backlog promote <id> --task <task-id> [--milestone <id>]— a pure terminal transition linking an already-existing task back to its backlog origin.--task/--milestonehere mean the promotion target only (milestone defaults to the active one). This command never runstask-add/milestone-additself — create the real task or milestone first, through the normal human-confirmed pipeline, then promote the backlog item to close the loop.backlog archive <id> --reason <text>— a pure terminal transition, no--milestone/--task(archiving names no other work).
Both promoted and archived are terminal — pending is the only status
either transition starts from.
.pitway/backlog.yaml is the authoritative backlog state, committed
alongside whatever commit the workflow next produces — never a dedicated
commit of its own, and never left dirty in a way that breaks a task's own
clean-tree check. An item added while no milestone is active rides the next
milestone-confirm baseline commit (M045); no chore commit is needed.
See ../protocol-driver.md's "Choosing a correction mechanism" section for
when to reach for backlog instead of task-add or a quick-change. Run
pitway backlog --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 · 60 lines · 0 tokens per session scan A 67456785cd58
backlog 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 814 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
discuss
Conducts Jobs-to-be-Done analysis, UX journey design, and requirements gathering through interactive discovery. Use when starting feature analysis, defining user stories, or creating acceptance criteria.
help
Show help for Ralph Specum plugin commands and workflow.
continue
Detects current wave progress for a feature and resumes at the next step. Scans docs/feature/ for artifacts.
resume-project
Run resume-project now — Now / Blocked / Next. Not a cheat sheet.
epic-plan
Run /epic-plan — see .claude/commands/epic-plan.md for the authoritative spec.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.