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/aratkruglik/claude-sdlc/batchgit clone --depth 1 https://github.com/AratKruglik/claude-sdlcWrote 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/aratkruglik/claude-sdlc/batch)<a href="https://agentmods.dev/commands/aratkruglik/claude-sdlc/batch"><img src="https://agentmods.dev/badge/commands/aratkruglik/claude-sdlc/batch.svg" alt="Measured on agentmods" 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 | $0.00026 | $0.00674 |
| Opus 5 | $0.00013 | $0.00337 |
| Sonnet 5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
batch 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdlc:batch
Parallel SDLC pipeline runner. Analyzes scope, decomposes into independent tasks, dispatches worktree-isolated pipelines in parallel (or sequentially for dependent tasks).
Mandatory execution protocol
Step 1 — Validate and parse input
If $ARGUMENTS is empty: print usage and stop:
Usage: /sdlc:batch "Task description 1" "Task description 2" ...
/sdlc:batch --file=sprint-tasks.md
/sdlc:batch --dry-run "Task 1" "Task 2"
Parse flags from $ARGUMENTS:
--file=PATH: read task list from that file. Strip the flag.--stack=NAME: remember asforced_stack. Strip the flag.--dry-run: setdry_run = true. Strip the flag.
If --file=PATH provided: read the file. Extract tasks — one per non-blank line; strip leading - if present; skip markdown headers.
Otherwise: tasks are quoted strings in $ARGUMENTS. If no quoted strings, treat the entire remaining argument as a single task.
Print verbatim:
▶ /sdlc:batch
Tasks: <N tasks parsed>
Forced stack: <forced_stack or "auto-detect">
Dry run: <yes|no>
Step 2 — Invoke the batch-pipeline skill
Use the Skill tool to load and execute the batch-pipeline skill. Pass:
- Parsed task list
forced_stackflagdry_runflag
Do not improvise or inline the batch logic — delegate to the skill.
Step 3 — Hard rules during batch
- Do NOT edit project source files directly. Worker agents handle that inside their worktrees.
- Do NOT skip the cost-estimate confirmation (Step 3 in the skill). Always wait for user
yes/adjust/abort. - Do NOT continue to the next group if ALL tasks in the previous group failed — ask the user first.
- Do NOT proceed if worktree creation fails for all tasks in a group.
Step 4 — On unrecoverable failure before dispatch
If batch setup fails before any worktrees are created:
- Print:
⛔ Batch halted: <reason> - Stop. No partial telemetry needed.
Examples
/sdlc:batch "Add /healthz endpoint" "Fix typo in README" "Rename /api to /v1"
/sdlc:batch --file=sprint-tasks.md
/sdlc:batch "Add billing [complex]" "Fix login redirect [simple]"
/sdlc:batch "Implement subscription billing" --dry-run
/sdlc:batch --stack=nodejs "Add auth middleware" "Add rate limiting"
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 · 72 lines · 26 tokens per session scan A 030ba03b9c9c
batch is a command published in the GitHub repository AratKruglik/claude-sdlc (32 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 674 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 2026-09-03.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.