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 agentmods add skills/amanning3390/hermeshub/react-reasoningnpx skills add amanning3390/hermeshub --skill react-reasoninggit clone --depth 1 https://github.com/amanning3390/hermeshubWrote 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/amanning3390/hermeshub/react-reasoning)<a href="https://agentmods.dev/skills/amanning3390/hermeshub/react-reasoning"><img src="https://agentmods.dev/badge/skills/amanning3390/hermeshub/react-reasoning.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.02583 |
| Opus 5 | $0.00043 | $0.01291 |
| Sonnet 5 | $0.00017 | $0.00517 |
| Haiku 4.5 | $0.00009 | $0.00258 |
Grade A, and why
react-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 5d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ReAct Reasoning
Synergize reasoning and acting in an interleaved loop. Based on the ReAct framework (Yao et al., ICLR 2023).
When to Use
- Multi-hop question answering that requires external knowledge retrieval
- Fact verification where claims must be checked against real sources
- Any task where chain-of-thought alone hallucinates facts
- Interactive decision making in complex environments (web navigation, file systems, APIs)
- Tasks requiring dynamic plan adjustment based on intermediate observations
- Situations where the agent needs to "think out loud" while taking actions
Core Concept
Human intelligence combines task-oriented actions with verbal reasoning (inner speech). ReAct replicates this by augmenting the agent's action space with a thought action — free-form language that does not affect the external environment but updates the agent's working context.
Standard action space: A = {search, lookup, click, finish, ...}
ReAct action space: Â = A ∪ L (where L = language/thought space)
A thought (ˆa ∈ L) composes useful information by reasoning over the current context. It produces no external observation but updates the trajectory context for future steps.
The Thought-Action-Observation Loop
Every task is solved through an interleaved sequence:
Thought 1 → Action 1 → Observation 1 → Thought 2 → Action 2 → Observation 2 → ... → finish[answer]
Thought Types
Use thoughts for these purposes (mix freely):
| Purpose | Example |
|---|---|
| Decompose goals | "I need to find X, then compare it with Y, then determine Z." |
| Extract from observations | "The paragraph says X was founded in 1844." |
| Commonsense reasoning | "X is not Y, so the answer must be Z instead." |
| Arithmetic reasoning | "1844 < 1989, so X came first." |
| Track progress | "I found X and Y. I still need Z." |
| Handle exceptions | "The search returned nothing useful. Let me reformulate as Q." |
| Synthesize answer | "Based on Obs 1-3, the answer is X because..." |
What ships with it
1 file 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.
- 5d ago First seen · 255 lines · 85 tokens per session scan A c76a4a1acecf
react-reasoning is a skill published in the GitHub repository amanning3390/hermeshub (34 stars, last pushed 2mo ago), licensed MIT. It adds 85 tokens to every session and 2,583 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…