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/deep-research)<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/deep-research"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/deep-research/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/deep-research"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/deep-research.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 | $0.00010 | $0.00920 |
| Opus 5 | $0.00005 | $0.00460 |
| Sonnet 5 | $0.00002 | $0.00184 |
| Haiku 4.5 | $0.00001 | $0.00092 |
Grade A, and why
deep-research 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 10d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research: $ARGUMENTS
Conduct comprehensive research using Time-Tested Diffusion (TTD) methodology.
Context Isolation: This command invokes the
conducting-deep-researchskill which runs in a forked context. Multiple research iterations, source evaluations, and draft refinements happen in isolation, preventing context pollution while delivering final results to the main conversation.
Step 1: Research Brief
Create a structured brief:
RESEARCH BRIEF
Topic: [derived from request]
Key Questions:
1. [Primary]
2. [Secondary]
3. [Tertiary]
Constraints: [limits]
Step 2: Initial Draft
Write from existing knowledge. Mark uncertainty:
[NEEDS VERIFICATION]- unsure claims[RESEARCH NEEDED]- gaps[CONFIDENCE: LOW/MED/HIGH]
Step 3: Red Team Critique
Attack your draft for:
- Logical fallacies (circular reasoning, false dichotomies)
- Evidence gaps (unsourced, single-source)
- Coverage gaps (missing perspectives)
Rate each issue 1-10 severity.
Step 4: Research with Reflection
CRITICAL: After EVERY search, reflect:
REFLECTION:
- Key facts: [with confidence 1-100]
- Gaps remaining: [what's missing]
- Source agreement: [contradictions?]
- Decision: [search again / move on / done]
Step 5: Source Tracking
Track every fact:
FACT: [Statement]
SOURCE: [URL]
CONFIDENCE: [1-100]
DISPUTED: [Yes/No]
Step 6: Quality Evaluation
Score after each cycle:
- Comprehensiveness (1-10)
- Accuracy (1-10)
QUALITY LOG:
Iteration 1: Comp [X], Acc [Y], Avg [Z]
If average < 7: repeat critique → research → refine (max 3 cycles)
Step 7: Final Report
# [Title]
## Executive Summary
[2-3 paragraphs]
## Findings
[with inline citations]
## Methodology
[sources, confidence approach]
## Limitations
[gaps, disputes]
## Sources
[numbered with confidence]
User Interaction
Use the AskUserQuestion tool when:
- Topic is ambiguous or has multiple interpretations
- Scope needs clarification (timeframe, geography, focus area)
- Quality threshold preferences should be confirmed
- Contradictions require user judgment to resolve
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.
- 10d ago First seen · 153 lines · 10 tokens per session scan A 0dadff7395ae
deep-research is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 920 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.