Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Nafjan/summonnpx agentmods add skills/nafjan/summon/deliberateWrote 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/skills/nafjan/summon/deliberate)<a href="https://agentmods.dev/skills/nafjan/summon/deliberate"><img src="https://agentmods.dev/badge/skills/nafjan/summon/deliberate/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/skills/nafjan/summon/deliberate"><img src="https://agentmods.dev/badge/skills/nafjan/summon/deliberate.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 | $0.00036 | $0.00515 |
| Opus 5.5 | $0.00014 | $0.00206 |
| Sonnet 5.5 | $0.00007 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
deliberate 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 26d 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.
What it actually says
Deliberate — governed decisions for Summon
/deliberate is the focused companion entry point for Summon's governed-decision
workflow. It owns no scheduler, scripts, schemas, or duplicate policy. Read the
canonical guide at ../summon/references/deliberation.md before constructing,
inspecting, recovering, or resuming a run.
Use /deliberate when a decision has explicit options and named seats and must be
bounded by quorum, physical attempts, an absolute deadline, and a durable journal.
Use /summon for ordinary dispatch, manifest/fan-out, and council work. Council
remains the right choice for cross-examination and a chairman's synthesis.
Before invoking it, obtain—not infer—the question, 2–10 seat IDs, at least two option IDs, quorum, rounds, maximum physical attempts, deadline, human-approval policy, private durable run directory, and each seat's authority/consent/worktree evidence. If any of those facts are missing, ask the user or choose another mode.
The CLI is the same dispatcher:
../summon/scripts/run_subagent.py deliberate --question "…" --seats A,B \
--options X,Y --quorum all --rounds 1 --max-attempts 2 --deadline 30m \
--run-dir <private-runs-root> --cwd <project>
The fresh provider path is limited to an explicit quorum, one round, one physical
attempt per seat, and enforceable read-only subprocess seats with executable
evidence. Unsupported configurations refuse before provider contact; the lane
never silently retries, falls back, or changes mode. The example's two seats
therefore use --max-attempts 2. These are runtime admission constraints, not
proof of current provider availability or served-model identity.
deliberate resume and human approval remain integration_pending. status,
replay, recover, cancel, and open are provider-inert. An unmatched physical
start is uncertain_spend; --retry-indeterminate only acknowledges that
uncertainty and does not activate the gated resume path or grant launch permission.
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.
- 26d ago Changed · +7 lines 367e615197a1
- 1mo ago First seen · 37 lines · 36 tokens per session scan A 02ef3d48db4a
deliberate is a skill published in the GitHub repository Nafjan/summon (4 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 515 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 2026-08-31.
Other skills, from other repositories
agent-builder
Build production-ready LLM agents with LangGraph, tool use, memory, streaming, and error handling. Use when designing or implementing an AI agent, multi-agent system, or agentic workflow.
clinicaltrials-database
Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data, for clinical research and patient matching.
openalex-database
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly…
glycoengineering
Analyze and engineer protein glycosylation. Scan sequences for N-glycosylation sequons (N-X-S/T), predict O-glycosylation hotspots, and access curated glycoengineering tools (NetOGlyc, GlycoShield, GlycoWorkbench). For glycoprotein engineering, therapeutic antibody optimization, and vaccine design.
tinker-training-cost
Calculates training costs for Tinker fine-tuning jobs. Use when estimating costs for Tinker LLM training, counting tokens in datasets, or comparing Tinker model training prices. Tokenizes datasets using the correct model tokenizer and provides accurate cost estimates.
pandic-office
Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.