Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mumerfarooq-con/asdlc-tools/plugin install asdlcWrote 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/mumerfarooq-con/asdlc-tools/implement-prd)<a href="https://agentmods.dev/commands/mumerfarooq-con/asdlc-tools/implement-prd"><img src="https://agentmods.dev/badge/commands/mumerfarooq-con/asdlc-tools/implement-prd/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/mumerfarooq-con/asdlc-tools/implement-prd"><img src="https://agentmods.dev/badge/commands/mumerfarooq-con/asdlc-tools/implement-prd.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 | $0.00041 | $0.01547 |
| Opus 5.5 | $0.00016 | $0.00619 |
| Sonnet 5.5 | $0.00008 | $0.00309 |
| Haiku 4.5 | $0.00004 | $0.00155 |
Grade A, and why
implement-prd 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 4d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are orchestrating work for: $ARGUMENTS
Parse the arguments and pick a mode:
--review-onlypresent → Retrospective mode (arg is a PRD).--plan-onlypresent → Plan-only mode (arg is a PRD).--executepresent → Execute mode (arg is a PLAN file).- otherwise → Pipeline mode (arg is a PRD).
You coordinate only — route all planning, coding, review, and testing through subagents to keep your context small.
Pipeline mode (fresh PRD implementation)
-
Plan — Invoke
prd-planneron the PRD. Wait for the plan file path and status.- If
STATUS: BLOCKED, surface the open questions to the user and STOP.
- If
-
Execute → Review → Test loop — For each task in dependency order: a. Invoke
prd-executorwith the plan path and task name.- If BLOCKED, surface to the user and pause.
b. Invoke
prd-reviewerin task mode on the same task. - On
REVIEW: CHANGES_REQUESTED, re-invokeprd-executorwith the findings. Max 2 fix attempts, then escalate to the user. c. OnREVIEW: APPROVED, invokeprd-testeron the task. - On
TEST: FAIL, re-invokeprd-executorwith the failure report, then re-run the reviewer ONLY if the fix touched files beyond the original task scope; otherwise go straight back to the tester. Max 2 fix attempts, then escalate. d. OnTEST: PASS, proceed to the next task.
Independent tasks (no shared files, no dependency edge) may execute in parallel; review and test steps still run per task.
- If BLOCKED, surface to the user and pause.
b. Invoke
-
Wrap up — When all tasks are DONE + APPROVED + PASS:
- Run the full test suite once from the main session as a sanity check.
- Summarize: tasks completed, files changed, tests added, review findings deferred (MINORs), anything flagged.
- Suggest a commit message (do not commit unless asked).
Plan-only mode (--plan-only) — produce a plan and STOP
Nothing is implemented in this mode. Approval is not interactive; it lives in the plan file.
- Pick the plan id
<ID>: the ticket key in the PRD's title if it has one (e.g.PROJ-142), else the PRD file's basename. Invokeprd-planneron the PRD and tell it the exact output path:./plans/<ID>.plan.md.- If
STATUS: BLOCKED, surface the open questions and STOP.
- If
- Stamp it:
${CLAUDE_PLUGIN_ROOT}/scripts/plan-state.sh stamp ./plans/<ID>.plan.md <ID>(writes the header block,status: pendingplus a hash of the plan, and adds an empty Progress section after a<!-- asdlc:progress -->line. The hash covers only what's above that line, so what a run logs there never voids the approval). Stamp adds that line itself and refuses a plan that already contains one, so the plan must not have it. - Tell the user the plan is written and awaiting approval. To approve: open the file, read the
plan, and set
status: approvedin the header block — then run/asdlc:implement-prd ./plans/<ID>.plan.md --execute(/asdlc:jira-runalso picks up approved plans for Jira tickets). STOP.
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.
- 4d ago Changed · +13 lines 997d2130dbe9
- 9d ago Changed · +30 lines · +14 tokens per session bb38bce820b4
- 1mo ago First seen · 43 lines · 27 tokens per session scan A 76aa68afc5f9
implement-prd is a command published in the GitHub repository mumerfarooq-con/asdlc-tools (2 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 1,547 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other commands, from other repositories
poc
Before building on an unproven idea, get a timeboxed yes/no answer — start a hypothesis-driven POC that skips 80% of the production pipeline and forces ship/pivot/kill at expiry, then promote a shipped POC through the audits it skipped.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
rfc
RFC process for cross-team decisions. Create, track, and close RFCs. Accepted RFCs auto-create ADRs.
exception
Signed gate-exception registry — replace ad-hoc --admin / --no-verify bypasses with an auditable, signed, expiring record (who · why · gate · scope · expiry). Create / list / check exceptions.
lucius
Segunda opinión técnica externa vía Codex CLI — diagnóstico y prescripción por ítem.
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.