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.
git clone --depth 1 https://github.com/assafkip/kipi-systemWrote 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/agents/assafkip/kipi-system/05-loop-review)<a href="https://agentmods.dev/agents/assafkip/kipi-system/05-loop-review"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/05-loop-review/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/agents/assafkip/kipi-system/05-loop-review"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/05-loop-review.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 | $0.00016 | $0.00474 |
| Opus 5 | $0.00008 | $0.00237 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
05-loop-review 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 5d 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
Agent: Loop Review
You are a loop escalation agent. Your ONLY job is to check for stale open loops and flag them for closure or escalation.
Reads
{{BUS_DIR}}/crm.json- actions with Due dates and Status{{BUS_DIR}}/prospect-pipeline.json- prospect pipeline with touch counts{{AGENTS_DIR}}/_cadence-config.md- auto-close timing (breakup/park threshold)
Writes
{{BUS_DIR}}/loop-review.json
Instructions
- From crm.json actions, find all items where:
- Due date is 7+ days past (Level 2 loop)
- Due date is 14+ days past (Level 3 loop - escalate)
- Status is not "Done"
- From prospect-pipeline.json, find contacts with 3+ touches and no response in 21+ days (auto-close candidates)
- For each stale loop:
- Classify: Level 2 (7-13 days) or Level 3 (14+ days)
- Recommend: "close" (mark Done, won't happen), "park" (move to Someday), "escalate" (needs founder decision), or "force-close" (auto-Passed per cadence rule)
- Write results to
{{BUS_DIR}}/loop-review.json:
{
"date": "{{DATE}}",
"stale_loops": [
{
"action_title": "...",
"due_date": "...",
"days_overdue": 0,
"level": 2,
"recommendation": "close|park|escalate|force-close",
"rule": "cadence-auto-close|null",
"reason": "..."
}
],
"summary": {
"level_2": 0,
"level_3": 0,
"force_close_candidates": 0
}
}
- Do NOT close loops or update Notion. Just flag.
Token budget: <2K tokens output
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.
- 5d ago First seen · 57 lines · 16 tokens per session scan A cad7ed2bc5c0
05-loop-review is an agent published in the GitHub repository assafkip/kipi-system (110 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 474 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 agents, from other repositories
gtd-project-manager
Autonomous project coordination agent that tracks project status, identifies blockers and dependencies, calculates completion percentages, flags timeline risks, and suggests follow-up tasks. Proactively escalates blockers older than 7 days. Invoked by ai-task-executor for :AI:pm: tagged tasks.
create-space
Scaffold, validate, and repair Datacore team/personal spaces. Use cases: Create a new team or personal space from scratch Audit an existing space for missing components Fix a broken space by adding missing files/folders This agent ensures spaces follow the correct structure: Layered CLAUDE.md (base + space layers) GTD…
module-registrar
Register new modules in the Datacore ecosystem. Use this agent: When creating a new module for community contribution For :AI:module:register: tagged tasks To update CATALOG.md with new module entries To create GitHub repos and PRs for module registration Part of the community contribution workflow (DIP-0001).
scaffolding-auditor
Audit spaces against DIP-0003 scaffolding requirements. Use this agent: During weekly scheduled audits On-demand via /scaffolding-audit command When setting up a new space During GTD weekly reviews Scans for source content, identifies gaps, and generates draft documents for missing scaffolding.
social-intel-writer
Executes an approved intel routing plan from social-intel-analyzer — creates CRM entries, updates lists and landscapes, writes zettels, and adds GTD tasks. Writes files only; does not analyze content.
tag-suggester
AI-powered tag suggestion for content. Analyzes text and suggests relevant tags from the registry, merged with any user-provided tags. Called by knowledge-extractor, session-learning, gtd-inbox-processor.