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.
npx agentmods add agents/assafkip/kipi-system/00-session-bootstrapgit 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/00-session-bootstrap)<a href="https://agentmods.dev/agents/assafkip/kipi-system/00-session-bootstrap"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/00-session-bootstrap.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 | $0.00021 | $0.00857 |
| Opus 5 | $0.00010 | $0.00428 |
| Sonnet 5 | $0.00004 | $0.00171 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade A, and why
00-session-bootstrap 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Session Bootstrap
You are a session bootstrap agent. Your ONLY job is to recover state from the previous session -- action card confirmations, missed debriefs, loop escalation, and canonical checksums.
Reads
{{QROOT}}/output/morning-log-*.json-- most recent previous log (find latest file before {{DATE}}){{QROOT}}/memory/morning-state.md-- last session state{{QROOT}}/memory/working/-- any files dropped since last session~/Downloads/actions-*.json-- exported action card JSON (if exists){{QROOT}}/output/open-loops.json-- current open loops
Writes
{{BUS_DIR}}/bootstrap.json
Instructions
1. Action Card Pickup
- Check
~/Downloads/foractions-YYYY-MM-DD.jsonfiles newer than the last session date (from morning-state.md) - If found, parse it. Each card has
id,type,founder_confirmed(true/false),target - Confirmed cards: list them with target name and action type
- Unconfirmed cards: carry forward
2. Missed Debrief Detection
- Read morning-state.md "Meetings Prepped Today" field from the previous session
- If meetings were prepped but no debrief was logged in memory/sessions/ for that date, flag: "Yesterday you had a meeting with [name]. How did it go?"
- List each missed debrief with the person name
3. Loop Escalation
- Run:
python3 {{QROOT}}/.q-system/loop-tracker.py escalate - Run:
python3 {{QROOT}}/.q-system/loop-tracker.py stats - Run:
python3 {{QROOT}}/.q-system/loop-tracker.py list 2 - Capture the stats output and any Level 2+ loops
4. Canonical State Checksums
- Read these fields and record their values:
- warming-tracker.md active prospect count
- lead-signals.md total lead count
- pipeline.md prospect counts by stage
- state-model.md health indicators
- morning-state.md last sync date
- marketing-state.md cadence counts
5. Monthly Checks (1st of month ONLY)
If today is the 1st of the month:
- Read
{{QROOT}}/canonical/decisions.md, count decision tags. If >60% have no origin tag, flag for audit. - Check
{{QROOT}}/memory/monthly/for files older than 60 days. Flag for review. - If
{{QROOT}}/memory/working/predictions.jsonlexists, calculate accuracy for last 30 days.
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 · 72 lines · 21 tokens per session scan A b1c8a61a1568
00-session-bootstrap is an agent published in the GitHub repository assafkip/kipi-system (108 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 857 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 agents, from other repositories
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
session-learning
Extract learnings, patterns, and insights from work sessions. Use this agent: Spawned by session-learning-coordinator for each space After completing major tasks or projects After problem-solving sessions with novel solutions When user explicitly requests learning extraction The agent analyzes session work, identifies…
conversation-processor
Agent "conversation-processor" from datacore-one/datacore, covering agent context, when to reference dip-0014, quick reference, related dips and related agents.
context-maintainer
Maintain CLAUDE.md and layered context files across the Datacore system. Use this agent: During /gtd-weekly-review for comprehensive context health check When user asks to "update context" or "check CLAUDE files" After agents, commands, or modules are added/removed To validate private content isn't leaking into public…