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/oleg494/coding-kit/reasoning-enginenpx skills add oleg494/coding-kit --skill reasoning-enginegit clone --depth 1 https://github.com/oleg494/coding-kitWhat 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 | $0.00059 | $0.00895 |
| Opus 5 | $0.00030 | $0.00447 |
| Sonnet 5 | $0.00012 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00089 |
Grade A, and why
reasoning-engine scanned grade A with 1 finding 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 yesterday.
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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Verify instrumentally.** Numbers and facts — via search/code/curl, not from memory. How it starts
The opening of the file, as written. The whole thing — 102 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
Always-on skill. Apply before every non-trivial action.
1. Multi-Step Thinking Protocol
Before ANY non-trivial action — think 5 steps ahead:
CURRENT STEP
│
├── Step +1: What happens after this?
│ ├── Option A: success → what next?
│ ├── Option B: partial success → plan B?
│ └── Option C: failure → rollback?
│
├── Step +2: And then what?
├── Step +3: Final goal?
├── Step +4: What can break?
└── Step +5: How to lock in the result?
Rule: at least 3 options for each step. Each option — a risk assessment.
2. Evidence-First Protocol
- Facts from the primary source. An answer from memory = a hypothesis. Mark "verify".
- 1 source = not an answer. Minimum 2 for any key fact.
- Verify instrumentally. Numbers and facts — via search/code/curl, not from memory.
- Dating. Say when the data is current: "As of 2026..."
- Counter-argument. What if I'm wrong? Formulate it and check it.
- If unsure — say so. "Couldn't find confirmation, double-check manually."
- After answering — check again. If you find an error — fix it.
3. Complexity Classifier
- LIGHT: 1-3 actions, everything known → answer immediately.
- MEDIUM: 4-10 actions → load skills, check memory (Wiki).
- COMPLEX: >10 actions, high cost of error → full fable-method + reasoning.
4. Skill-First Mandate
Zero rule: writing code/a solution from scratch when a skill exists = failure.
Before ANY non-trivial task:
- Check
skills/— is there a skill for the task? (look atdescriptionin frontmatter) - Load the primary skill →
read skills/<name>/SKILL.md - Follow the protocol from the skill
- Note the usage:
📚 skill-name
If a skill exists but you didn't use it — you messed up. Redo it.
5. Memory-First Protocol
Cross-chat memory = a database, not a conversation.
Before answering "what do we know about X":
python ../memory/db-tools/search_all.py "X" # SEARCH FIRST
- Found → answer with a link to the file.
- Not found → honestly say "not in the database".
- NEVER answer from conversation memory.
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.
- yesterday First seen · 102 lines · 59 tokens per session scan A 89509ccf7df9
reasoning-engine is a skill published in the GitHub repository oleg494/coding-kit (1 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 895 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
run
Execute a named agent role with optimized instructions. Explicit invocation only ($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…