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/assafkip/prd-os/prd-splitgit clone --depth 1 https://github.com/assafkip/prd-osWhat 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 | $0.00012 | $0.00318 |
| Opus 5 | $0.00006 | $0.00159 |
| Sonnet 5 | $0.00002 | $0.00064 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
prd-split scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to prd-split — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Materialize the PRD's ## Issues fenced JSON manifest into issue specs under
issues_dir. The split script enforces:
- PRD status is
approved. - Every entry has non-empty
allowed_filesand non-emptyrequired_checks. (An emptyrequired_checkssilently bypasses the runner's verification gate — the split refuses to create such specs.) - No existing issue file is clobbered. Re-runs are idempotent only when byte-identical.
Two-step flow — dry-run first so the author can see planned writes before any file lands on disk:
- Dry-run:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_split.py" --dry-run
Read the would_create paths back to the author. Confirm before committing.
If they do not confirm, stop. Do NOT run step 2 without explicit agreement.
- Commit:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_split.py"
On collision, the script names the divergent files. Do not delete or overwrite them. Ask the author to rename either the manifest entry or the existing file.
After a successful split, tell the author to archive or clear the PRD before
starting an issue (prd_runner.py archive or prd_runner.py clear). The
concurrency guard blocks loading an issue while a PRD context is active.
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 · 39 lines · 12 tokens per session scan A 000d7021e961
prd-split is a command published in the GitHub repository assafkip/prd-os (10 stars, last pushed 2mo ago), licensed MIT. It adds 12 tokens to every session and 318 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to prd-split, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
plan-phase
Wraps superpowers:writing-plans with RENATA guardrails to produce a method-compliant, ADR-respecting execution plan reviewed by the architect.
adopt
Adopts RENATA in an existing codebase — reverse-engineers the technical pattern, feature inventory, as-built specs and a retroactive PRD, confirming every item with you.
adr
Formalizes an ADR from a technical decision using the Nygard format and syncs its enforcement block in rules.yaml.
screens
Structures product UX screen design — inventory, flow, states, and reusable briefs for external design tools — without generating pixels or UI code.
assumption-test
Surfaces the riskiest business assumption behind the PRD and designs the cheapest test to falsify it before building.
bug-report
Converts a raw bug report from production into a structured, severity-classified item and routes it to the right next step.