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 skills add desy-design/AG3NT --skill deep-reasoninggit clone --depth 1 https://github.com/desy-design/AG3NTWrote 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/desy-design/ag3nt/deep-reasoning)<a href="https://agentmods.dev/skills/desy-design/ag3nt/deep-reasoning"><img src="https://agentmods.dev/badge/skills/desy-design/ag3nt/deep-reasoning/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/desy-design/ag3nt/deep-reasoning"><img src="https://agentmods.dev/badge/skills/desy-design/ag3nt/deep-reasoning.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 | $0.00024 | $0.02288 |
| Opus 5.5 | $0.00010 | $0.00915 |
| Sonnet 5.5 | $0.00005 | $0.00458 |
| Haiku 4.5 | $0.00002 | $0.00229 |
Grade A, and why
deep-reasoning 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.
This is a copy
100% identical to deep-reasoning — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Reasoning Skill
Use this skill when you need to think through complex problems systematically. The deep_reasoning tool helps you:
- Break down complex problems into manageable steps
- Explore multiple solution approaches (branching)
- Revise earlier thinking when new information emerges
- Generate and test hypotheses
- Track confidence levels in your conclusions
- Maintain structured reasoning across long analyses
When to Use Deep Reasoning
Use this tool when:
- The problem requires multiple steps to solve
- You need to explore alternative approaches
- Earlier assumptions might need revision
- You want to track confidence in your conclusions
- The problem involves hypothesis testing
- You need to maintain reasoning context across many steps
Don't use for:
- Simple factual lookups
- Single-step operations
- Tasks that don't benefit from structured thinking
The deep_reasoning Tool
Basic Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
thought |
string | Yes | Your current thinking step |
thought_number |
int | Yes | Current step number (1, 2, 3...) |
total_thoughts |
int | Yes | Estimated total steps needed |
next_thought_needed |
bool | Yes | True if more thinking needed |
Advanced Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
thought_type |
string | "regular" | Type: regular, hypothesis, verification, revision, branch, conclusion, question, evidence |
reasoning_mode |
string | "analytical" | Mode: analytical, creative, critical, exploratory, deductive, inductive, abductive |
confidence |
float | 0.7 | Confidence level (0.0 to 1.0) |
is_revision |
bool | false | Whether this revises a previous thought |
revises_thought |
int | null | Which thought number is being revised |
branch_from_thought |
int | null | Create a branch from this thought |
branch_id |
string | null | Identifier for the branch |
hypothesis_statement |
string | null | Propose a new hypothesis |
hypothesis_id |
string | null | Reference an existing hypothesis |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 292 lines · 24 tokens per session scan A 064acd58bdaf
deep-reasoning is a skill published in the GitHub repository desy-design/AG3NT (2 stars, last pushed 8d ago), licensed MIT. It adds 24 tokens to every session and 2,288 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to deep-reasoning, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
deep-reasoning
Structured multi-step reasoning tool for complex problem solving with branching, hypothesis testing, and evidence tracking.
qa-acceptance
Produce QA acceptance criteria and a manual validation plan for a feature change — golden path, edge cases, error states, performance limits, and explicit pass/fail evidence.
ultrathink
Activate extended thinking mode for complex problems - deep reasoning, chain-of-thought decomposition, multi-step analysis, and thorough exploration before answering.
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.