Borrowing it
Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/generate-tasks.mdgit clone --depth 1 https://github.com/bredmond1019/claude-sdk-rsWrote 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/bredmond1019/claude-sdk-rs/generate-tasks)<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/generate-tasks"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/generate-tasks/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/bredmond1019/claude-sdk-rs/generate-tasks"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/generate-tasks.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 | $0.08084 |
| Opus 5.5 | $0.00000 | $0.03234 |
| Sonnet 5.5 | $0.00000 | $0.01617 |
| Haiku 4.5 | $0.00000 | $0.00808 |
Grade A, and why
generate-tasks 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Tasks — Generate a task spec for a specified phase and block.
Variables
$ARGUMENTS — one of two input modes:
- Master-plan slug mode (default): the spec's planning/ directory name — its block
ID. Write new spec directories in the canonical form <REPO>.<phase>.<block>
(e.g. BA.0.A, EN.8.A) — a repo-unique two-or-three-letter code from brain.toml, a
phase number, and a block letter or number; the directory name equals the block ID
exactly, no title suffix. This is the form /generate-master-plan.md and /plan.md
author (see /generate-master-plan.md step 4 for the full rule). Legacy directories
still resolve for as long as they exist — older specs may be spelled
<phase>.<block>-<title> (e.g. 2.1-learn-paths-structural-fixes) or
<repo>-<phase><block>-<title>; this command does not require migrating them, it only
writes new ones canonically. The block definition is read from master-plan.md.
- Plan-file mode (--from <path> [phaseN-blockX]): decompose a block from a
standalone plan file instead of master-plan.md. The file may be either a single
standalone block definition (legacy D34) or a master-plan-format /plan output with
## Phase N / ### Block X headings. For a master-plan-format file, append the
phaseN-blockX selector to pick which block to decompose (required when the file has
more than one block). Used for ad-hoc / experimental features kept out of the roadmap
(see planning/decisions/D34-adhoc-planning-seam.md).
Required. If omitted, stop and say: "Usage: /generate-tasks <P.N-slug> (e.g.
), or /generate-tasks --from planning/plan-/plan.md [phaseN-blockX]"
Instructions
The three checks that can fail this command. They live in full in steps 6 and 8 below; they are hoisted here because they are the reason a spec is rejected, and they are easy to skim past in a long procedure.
- Compilable task boundaries — under
/sdlc-flowand/sdlc-taskevery task must leave the gating suite passing, so a breaking public-surface change may never be split across tasks. This outranks disjoint file ownership: the tasks merge, not the constraint.- Un-gateable acceptance criteria must be declared (D64) — any criterion whose evidence lives in another process, another repo, a generated artifact, or an installed artefact needs a named failing command or a dedicated fixture-evidence task. A green suite is never itself the evidence.
- Never fabricate a load-bearing fact — which files a task owns, an observable criterion, a real dependency edge. Ask in an interactive session; abort with a specific message in a preflight context.
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.
- 11d ago First seen · 464 lines · 0 tokens per session scan A 7a15885afff6
generate-tasks is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 8,084 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 2026-10-26.
generate-tasks compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| generate-tasksbredmond1019/claude-sdk-rs | Command | 23 | 1mo ago | Apache-2.0 | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |