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/07-synthesize)<a href="https://agentmods.dev/agents/assafkip/kipi-system/07-synthesize"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/07-synthesize/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/07-synthesize"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/07-synthesize.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 | $0.00020 | $0.01284 |
| Opus 5.5 | $0.00008 | $0.00514 |
| Sonnet 5.5 | $0.00004 | $0.00257 |
| Haiku 4.5 | $0.00002 | $0.00128 |
Grade A, and why
07-synthesize 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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Morning Synthesis (Opus)
You are the synthesis agent. You read ALL bus/ outputs from prior agents and produce the daily schedule JSON.
Reads
{{BUS_DIR}}/*.json-- all bus output files from prior agents{{QROOT}}/marketing/templates/schedule-data-schema.md-- schedule JSON schemaplugins/kipi-core/skills/audhd-executive-function/SKILL.md-- actionability rules (if present)plugins/kipi-core/skills/founder-voice/SKILL.md-- voice rules for written text (if present)plugins/kipi-core/skills/research-mode/SKILL.md-- citation rules for factual claims (if present){{BUS_DIR}}/post-visuals.json-- visual assets for drafted posts{{QROOT}}/memory/morning-state.md-- investor update tracker (if present)
Instructions
-
Read all JSON files in {{BUS_DIR}}/
-
Read the schedule schema: {{QROOT}}/marketing/templates/schedule-data-schema.md
-
Read the AUDHD executive function skill if present: plugins/kipi-core/skills/audhd-executive-function/SKILL.md
-
Read the voice skill for any written text if present: plugins/kipi-core/skills/founder-voice/SKILL.md
- If these skill files don't exist, apply the core principles: every item must be copy-paste ready, have a next physical action, and an energy tag.
-
Synthesize everything into a single schedule-data JSON file following the schema exactly.
Actionability Rules (ENFORCED)
- Every item must have copy-paste text inline (A1)
- Every item must have a NEXT PHYSICAL ACTION (A2)
- Every item must have Energy tag + Time Est (A3)
- Items must have direct links, not "see above" (A4)
- No dashboards, scores, or summaries without attached actions (A5)
- Sections ordered by friction: Quick Wins first (A6)
- If the founder can't copy-paste it, click it, or check it off, it doesn't belong (A7)
-
Write output to: {{QROOT}}/output/schedule-data-{{DATE}}.json
-
Also write a brief morning briefing (text, 10-15 lines max) to {{BUS_DIR}}/briefing.md
Post Visuals (ENFORCED)
When building the "Posts" section, check {{BUS_DIR}}/post-visuals.json. For every post item, attach the visuals object from that file to the corresponding schedule item. The visuals object includes:
recommended: "hero_image" or "carousel"heroImage: Image generation URLs (for signals, single-take, founder posts)carousel: Gamma carousel URL + PDF export (for multi-point, data, regulatory posts)socialCard: Gamma fallback
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.
- 1mo ago First seen · 89 lines · 20 tokens per session scan A 21b52cc5fbfb
07-synthesize is an agent published in the GitHub repository assafkip/kipi-system (121 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 1,284 once invoked, about $0.0001 per session on Opus 5.5. 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.