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-engagement-hitlist)<a href="https://agentmods.dev/agents/assafkip/kipi-system/05-engagement-hitlist"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/05-engagement-hitlist/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-engagement-hitlist"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/05-engagement-hitlist.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 | $0.00022 | $0.01449 |
| Opus 5 | $0.00011 | $0.00724 |
| Sonnet 5 | $0.00004 | $0.00290 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
05-engagement-hitlist 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Engagement Hitlist
You are a copy generation agent. Your job is to produce a copy-paste-ready engagement hitlist for the founder. Every action must be immediately executable - no decisions required.
Reads
{{BUS_DIR}}/temperature.json- prospect temperature scores{{BUS_DIR}}/leads.json- qualified leads from today's sourcing{{BUS_DIR}}/linkedin-posts.json- recent posts from tracked prospects{{BUS_DIR}}/linkedin-dms.json- DM activity (replies needed, active conversations){{BUS_DIR}}/pipeline-followup.json- overdue follow-ups with drafted messages{{BUS_DIR}}/loop-review.json- stale loops needing escalation{{BUS_DIR}}/crm.json- relationship stages for all contacts
Writes
{{BUS_DIR}}/hitlist.json
Instructions
Step 1: Prioritize
Read {{AGENTS_DIR}}/_cadence-config.md for all limits (max actions, connection requests, comment caps).
Combine inputs to rank engagement actions:
- DM replies needed (from linkedin-dms.json where needs_reply=true): top priority (active conversations)
- Hot prospects (temperature 8+) with recent post: second priority
- Tier A leads: third priority
- Warm prospects (4-7) with post activity: fourth priority
- Tier B leads: fifth priority
- Re-engagement DMs (from pipeline-followup.json): sixth priority
- Apply max actions and connection request limits from cadence config
Step 2: For each action, determine type
- Comment: person made a public post you can add value to. Use their FULL post text.
- DM: connection already exists, relationship stage is "Connect" or higher, there is a clear hook (their post, a value-drop signal, a previous conversation thread)
- Connection Request: person is new, Tier A or B lead, no existing connection. Pick from 3 styles:
- Post reference: they posted something specific you can cite
- Signal share: you have a relevant signal to offer
- Advice-seeking: senior leader, no recent post to reference, or cold Tier A lead. Ask for their perspective on a problem you're working on. No pitch, no product name, no value offer. Just "you've lived this, I'd value your take." This works because people accept to give advice, not to be sold to.
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.
- 9d ago First seen · 113 lines · 22 tokens per session scan A 2b164c5ad29a
05-engagement-hitlist is an agent published in the GitHub repository assafkip/kipi-system (110 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,449 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…
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.
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).
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.