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 assafkip/kipi-system/plugin install prd-osWrote 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/assafkip/kipi-system/prd-archive)<a href="https://agentmods.dev/commands/assafkip/kipi-system/prd-archive"><img src="https://agentmods.dev/badge/commands/assafkip/kipi-system/prd-archive.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 5.1 | $0.00015 | $0.00351 |
| Opus 5 | $0.00008 | $0.00176 |
| Sonnet 5 | $0.00003 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
prd-archive scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Archive the active PRD. The runner's G4 coverage gate blocks archive when any
accepted finding in the PRD's findings JSONL lacks a matching entry in the
issue-receipts file with prd_id set to the active PRD. Deferred findings
require a non-empty rationale; rejected findings pass through.
Do not edit the receipts file by hand. If the gate blocks, close the named
issues via /issue-closeout (which writes the receipts) and retry.
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_runner.py" archive
On success, the spec's frontmatter flips to status: archived and the active
PRD state is cleared. On block, surface stderr verbatim — the runner names
each uncovered accepted finding and the path of the receipts file.
Spillover (out-of-scope findings)
Before declaring the PRD done, run the standing gate and report spillover:
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_runner.py" spillover list
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/prd_runner.py" gates run
gates run fails while any spillover item is open (an out-of-scope finding that
was deferred or captured during this PRD). The PRD is not "done" until every
spillover item is resolved against a closed issue or explicitly voided. In the
archive report, list each spillover item touched, the issue that resolved it, the
fix, and how it affected the system.
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.
- 8d ago First seen · 36 lines · 15 tokens per session scan A b0b7b3c4994f
prd-archive is a command published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 15 tokens to every session and 351 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
today
Your AI Chief of Staff's morning briefing — the main product deliverable of Data.
tomorrow
End-of-day review and AI delegation — queue overnight nightshift work.
diagnostic
Command "diagnostic" from datacore-one/datacore, covering diagnostic, command context, when to reference dip-0002, quick reference and agents this command invokes.
sprint-start
You are the Sprint-Start Facilitator — you run the Monday kickoff ceremony.
sync
Command "sync" from datacore-one/datacore, covering sync, command context, when to reference dip-0010, quick reference and agents this command invokes.
outbox
Process the outbox queue and route content to destinations (archive, delivery, publish).