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/azrtydxb/procoder/backloggit clone --depth 1 https://github.com/azrtydxb/procoderWhat 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 | $0.00023 | $0.00609 |
| Opus 5 | $0.00012 | $0.00304 |
| Sonnet 5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
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 yesterday.
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
The user invoked /procoder:backlog with arguments: $ARGUMENTS
The command below is the procoder binary on PATH.
The backlog is where a spec-first project lives: milestones group epics, epics group user stories, and the story is the execution unit with the same rigor as a todo task. The todo list itself stays separate — it is for standalone work not born from a spec.
procoder backlog seed <spec> [--milestone <id>]— decompose a COMPLETE spec into an epic plus one story per acceptance criterion. Everything is PRINTED for you to review and write; the epic records the spec and a fingerprint of its acceptance criteria, so the board can flag drift when the contract changes later.procoder backlog milestone <title>/procoder backlog epic <title> [--milestone <id>]/procoder backlog story <title> --epic <id>— print the file for each level; write it, then fill the real content (a story needs a real description and testable acceptance criteria before work starts).procoder backlog bug <title> [--epic <id>] [--severity sN]— a defect is a story with a severity and a pre-seeded regression-test criterion; close refuses without the severity. Triage honestly: s1/s2 jump the queue, and the regression test is not optional.procoder backlog board— the tree: milestones → epics → stories with statuses, sprint tags, spec-drift flags, and orphans. Run this to orient before pulling work. The last line names the branch it read and counts the open stories the default branch holds that this checkout cannot see — the backlog is versioned like the code, so "nothing open" can mean "nothing open here".procoder backlog list— the flat listing, open items first.procoder backlog close story <id>— the quality controller: it REFUSES until the description is real, every acceptance criterion is checked, evidence is recorded, and the gate is clean. Fix what it names and rerun; never argue with a refusal by weakening criteria.procoder backlog close epic <id>— refuses while any of the epic's stories is open; warns on spec drift.procoder backlog close milestone <id>— refuses while any of its epics is open.
Sprints pull stories from the backlog — see /procoder:sprint. With
arguments, run the matching subcommand and act on its output. Without
arguments, run board and report the project's state.
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.
- yesterday First seen · 47 lines · 23 tokens per session scan A 1da6dc3b8cd1
backlog is a command published in the GitHub repository azrtydxb/procoder (196 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 609 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
story-new
Create a new story. It lands in the backlog until assigned to a cycle.
status
Show current Craft progress — cycles, stories, backlog in a rich dashboard view.
story-archive
Move a story from a cycle back to the backlog.
remediate
Close the debt the deterministic lanes cannot version-bump away: the grandfathered broken build, advisories with no direct upgrade path, the lint backlog, missing tests, missing docs. Each run plans that debt as finite work orders and works them in two tiers: deterministic recipes execute first at $0 (lockfile resync…
plan
Create a detailed work plan with DoD and save it in memory-bank.
adr
Create an Architecture Decision Record in memory-bank BACKLOG.