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 oleg494/coding-kit --skill reasoning-enginegit clone --depth 1 https://github.com/oleg494/coding-kitWrote 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/oleg494/coding-kit/reasoning-engine)<a href="https://agentmods.dev/skills/oleg494/coding-kit/reasoning-engine"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/reasoning-engine/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/oleg494/coding-kit/reasoning-engine"><img src="https://agentmods.dev/badge/skills/oleg494/coding-kit/reasoning-engine.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 | $0.00064 | $0.00985 |
| Opus 5.5 | $0.00026 | $0.00394 |
| Sonnet 5.5 | $0.00013 | $0.00197 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
reasoning-engine 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 2d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reasoning Engine — the core of the agent's thinking
Core reasoning spine (OPS §2); apply to non-trivial questions and actions when no task-specific skill covers them.
1. Reason to the next observable result
Define the requested outcome, the immediate action, its likely failure modes and the check that will distinguish success from failure. Explore alternatives when they change cost, correctness or reversibility; do not manufacture three options at every step. A small local change needs less process than a migration.
2. Evidence-first protocol
- Use the source that owns the fact: local definition for local behavior, current official documentation for an external API, measured output for performance.
- One authoritative source can settle a narrow fact. Corroborate disputed, high-impact or indirect claims; source counts are not a substitute for quality.
- Check genuine uncertainty using available tools before asking the user. State any unresolved uncertainty alongside the claim, not as an automatic stop.
- Record relevant version/date and what would refute a consequential decision.
- Stop investigating when the evidence resolves the decision; reopen it when new evidence or an invalidating change appears, not after an arbitrary turn count.
3. Complexity
Scale planning and verification by coupled outcomes, uncertainty and consequences. Use fable-method only for explicit invocation or an uncovered judgment task.
4. Demand-driven skills
Select a skill from its description when it resolves a concrete unanswered domain question. The core method is already in OPS; a broad trigger does not require another full workflow. Reuse loaded guidance and existing evidence. If routing missed useful guidance, address the actual gap without redoing valid work for ceremony.
Cross-references to other skills are pointers, not a load order: a helper loads only for an unresolved question in its domain, and loading one does not cascade into loading the others. The host's mandatory skill policy always wins over this thrift.
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.
- 2d ago Changed a80f8deb35ab
- 8d ago Changed · -3 lines · +19 tokens per session d912781056bf
- 11d ago Changed · +29 lines a99e2e6b7936
- 25d ago Changed a0f22e5693fc
- 26d ago Changed 0847f1df7fb2
- 1mo ago Changed b2efc9405388
- 1mo ago Changed · -28 lines · -14 tokens per session 056b88531bd3
- 1mo ago Changed 66eb687b7ed1
- 1mo ago Changed bc3e70740c22
- 1mo ago First seen · 105 lines · 59 tokens per session scan A 5879c5e44ae3
reasoning-engine is a skill published in the GitHub repository oleg494/coding-kit (3 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 985 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
run
Execute a named agent role with optimized instructions. Explicit invocation only ($run). Never trigger implicitly.
tip
Deliver a transformative life perspective shift and a productivity tip. Use when the user invokes /tip or wants non-technical inspiration or a fresh mental model.
agentic-security-review
Run a security and dependency audit for agent systems, tool-using AI apps, MCP/A2A integrations, or security-sensitive AI-generated code. Check slopsquatting risk, tool shadowing, rug pulls, memory/context poisoning, secrets, unsafe permissions, and common CWE patterns. Use when asked for security review, dependency…
agentic-spec
Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/internal/production tasks, produce SPEC.md, and configure focused AGENTS.md boundaries. Use when asked to write a spec, plan a feature, design an agent/system, define architecture, or create…
agentic-evals
Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality dimensions, gold-set criteria, and CI gates before or after implementation. Use when asked for tests first, an eval plan, success criteria, non-deterministic testing, LLM-as-judge setup, or…
agentic-production-readiness
Prepare an AI agent system for production operation. Cover SHIELD controls, sandbox/canary/production rollout, OpenTelemetry observability with GenAI semantic conventions, Agent Card drafting, governance, and post-deploy monitoring. Use for production readiness checks, go-live checklists, agent monitoring, agent…