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/synaptiai/synapti-marketplaceWrote 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/commands/synaptiai/synapti-marketplace/ledger-synthesize)<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/ledger-synthesize"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/ledger-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/commands/synaptiai/synapti-marketplace/ledger-synthesize"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/ledger-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 | $0.00014 | $0.01303 |
| Opus 5 | $0.00007 | $0.00651 |
| Sonnet 5 | $0.00003 | $0.00261 |
| Haiku 4.5 | $0.00001 | $0.00130 |
Grade A, and why
ledger-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 11d 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesize Evidence
Process evidence objects into structured insights through layered synthesis.
Two-Phase Synthesis: First,
pillar-synthesizeragents process each pillar independently. Then,cross-synthesizeridentifies connections and conflicts across pillars.
Arguments
$ARGUMENTS: Optional synthesis focus or pillar filter.
Optional flags:
--pillars <list>- Only synthesize specific pillars--skip-cross- Skip cross-pillar synthesis--focus <topic>- Prioritize insights on specific topic
Prerequisites
- Evidence collection complete (
/ledger-research) - Evidence gates passed (≥5 objects per active pillar)
- Evidence objects in
02-evidence/<pillar>/
Workflow
Phase 1: Per-Pillar Synthesis
-
Spawn Pillar Synthesizers
- One
pillar-synthesizerper active pillar - Agents run in parallel
- One
-
Each Agent:
- Loads all
EV-<pillar>-*evidence - Clusters by theme
- Identifies patterns
- Handles contradictions
- Extracts key insights
- Generates
SYN-<pillar>.md
- Loads all
-
Output: 8 synthesis documents in
03-synthesis/
Phase 2: Cross-Pillar Synthesis
-
Spawn Cross-Synthesizer
- Single agent after all pillar syntheses complete
-
Agent:
- Loads all
SYN-*.mddocuments - Maps cross-pillar connections
- Identifies cross-pillar conflicts
- Extracts emergent insights
- Generates decision candidates
- Identifies risk candidates
- Generates
CROSS-SYNTHESIS.md
- Loads all
-
Output:
03-synthesis/CROSS-SYNTHESIS.md
Example Usage
Full synthesis
/ledger-synthesize
Specific pillars only
/ledger-synthesize --pillars market,users,economics
Skip cross-synthesis
/ledger-synthesize --skip-cross
Focus on specific topic
/ledger-synthesize --focus pricing
Output
## Synthesis Complete
**Pillars Synthesized:** 8
**Total Insights:** 42
**Cross-Pillar Connections:** 12
**Conflicts Identified:** 5
### Per-Pillar Summary
| Pillar | Insights | Contradictions | Decisions Needed |
|--------|----------|----------------|------------------|
| market | 6 | 1 resolved | 2 |
| users | 7 | 2 (1 pending) | 3 |
| tech | 5 | 0 | 1 |
| competitors | 5 | 1 resolved | 2 |
| design | 4 | 0 | 1 |
| legal | 4 | 0 | 2 |
| ops | 5 | 1 resolved | 1 |
| economics | 6 | 1 pending | 3 |
### Cross-Pillar Highlights
**Key Connections:**
1. Market pricing ceiling ($30) constrains Economics margin targets
2. User power-user preference aligns with Tech capability focus
3. Competitor gap in enterprise aligns with Market enterprise TAM
**Key Conflicts:**
1. Target segment: Market (enterprise) vs Users (SMB) vs Economics (SMB)
2. Pricing model: Competitors (freemium) vs Economics (paid)
### Decision Candidates
1. DEC-scope-target-segment
2. DEC-pricing-model
3. DEC-ux-complexity-level
4. DEC-tech-architecture-choice
5. DEC-legal-gdpr-approach
### Risk Candidates
1. RISK-market-price-competition
2. RISK-tech-llm-cost-overrun
3. RISK-retention-expert-churn
### Next Step
Run `/ledger-decide` to make explicit decisions with trade-offs.
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.
- 11d ago First seen · 197 lines · 14 tokens per session scan A 85264b6324b3
ledger-synthesize is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 1,303 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 2026-08-31.
Other commands, from other repositories
create-worktree
Follow these steps to create a git worktree.
paper-trail-review
Review and arbitrate problematic references (cascade-exhausted, unresolved UID, awaiting OCR). Generates an up-to-date report, walks through cases by category, and applies arbitration decisions to the registry.
paper-trail-new-paper
Start writing an academic paper (IMRaD structure) on a topic, with anti-hallucination citation verification at every step. Builds on existing audited SOTAs.
paper-trail-registry-cleanup
Nettoyage historique du registre des fiches bibliographiques (les 900 fiches existantes). Cible les vieilles fiches mal nommées (0000, untitled) ET les duplicates avec suffixes numériques (foo2020bar2, 234) qui sont des artefacts de runs INGEST passés. Délègue les décisions au sub-agent textbook-resolver. Les merge…
paper-trail-cascade
Acquire PDFs via the 8-source cascade (11 with opt-in extended sources) for a single ref by slug, or a batch filtered by state. Validates page 1 anti-homonymy on each download.
cc-refactor
(Conductor) Refactor a file or module for clarity and simplicity.