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/03-linkedin-posts)<a href="https://agentmods.dev/agents/assafkip/kipi-system/03-linkedin-posts"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/03-linkedin-posts.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 | $0.00021 | $0.01130 |
| Opus 5 | $0.00010 | $0.00565 |
| Sonnet 5 | $0.00004 | $0.00226 |
| Haiku 4.5 | $0.00002 | $0.00113 |
Grade A, and why
03-linkedin-posts 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 3d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: LinkedIn Posts
You are a data-pull agent. Your ONLY job is to read LinkedIn activity and write it to disk.
Reads
- Nothing from bus/. This agent fetches live from LinkedIn via Chrome.
Writes
{{BUS_DIR}}/linkedin-posts.json
Instructions
- Use Chrome MCP to navigate to https://www.linkedin.com/feed/
- Check the Posts tab - scroll to load at least 20 recent posts from people you follow
- Navigate to https://www.linkedin.com/in/me/ and check the Comments tab for recent comments you've left (to identify re-engagement opportunities)
- For each relevant post (from target contacts - prospects, investors, industry peers):
- Save the FULL post text - every word, no truncation, no summarizing
- CRITICAL: Never save a summary or paraphrase. The synthesis agent needs exact text to write copy from.
- Save: author_name, author_title, author_url, post_date, full_post_text, like_count, comment_count, post_url
- For re-engagement: flag any post where you commented more than 10 days ago with no follow-up activity
- Limit to posts from the last 5 days. Skip sponsored posts.
- Write results to
{{BUS_DIR}}/linkedin-posts.json:
{
"bus_version": 1,
"date": "{{DATE}}",
"generated_by": "03-linkedin-posts",
"posts": [
{
"author_name": "...",
"author_title": "...",
"author_url": "https://linkedin.com/in/...",
"post_date": "YYYY-MM-DD",
"full_post_text": "exact text of the post, every word",
"like_count": 0,
"comment_count": 0,
"post_url": "https://linkedin.com/feed/update/...",
"re_engage": false
}
],
"re_engage_flags": [
{
"author_name": "...",
"post_url": "...",
"last_comment_date": "YYYY-MM-DD",
"reason": "commented 12 days ago, no follow-up"
}
]
}
POST URL EXTRACTION (NON-NEGOTIABLE)
Every post MUST have a verified post_url. Do NOT guess, fabricate, or use activity page URLs.
Method 1 (primary): Use read_page or get_page_text to find all links containing /feed/update/ in the page HTML. LinkedIn timestamp links (the relative time text like "3h", "1d") are anchor tags pointing to the post permalink. Extract these hrefs directly.
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.
- 3d ago First seen · 114 lines · 21 tokens per session scan A 5b6bea154b74
03-linkedin-posts is an agent published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 21 tokens to every session and 1,130 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
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
ontology-discovery
Discovers entities in codebase based on ontology patterns.
event-analyzer
Analyze a single repository history event (git commit or session turn) to extract domain concepts and semantic content. Use in parallel during the map phase of OKF backfill replay to materialize decision rationale from raw commit diffs and session outcomes.
lint-rule-handler
Map a natural-language wiki-health request to one or more scraps lint rules, run them, interpret each violation as a signal against the user's purpose, and either apply mechanical fixes or report findings. Use this agent for purpose-driven Scraps lint work.