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/nitinbhide/tcaitoolkit/thinking-craftsman-skillnpx skills add nitinbhide/tcaitoolkit --skill thinking-craftsman-skillgit clone --depth 1 https://github.com/nitinbhide/tcaitoolkitWrote 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/nitinbhide/tcaitoolkit/thinking-craftsman-skill)<a href="https://agentmods.dev/skills/nitinbhide/tcaitoolkit/thinking-craftsman-skill"><img src="https://agentmods.dev/badge/skills/nitinbhide/tcaitoolkit/thinking-craftsman-skill.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 | $0.00042 | $0.01747 |
| Opus 5 | $0.00021 | $0.00873 |
| Sonnet 5 | $0.00008 | $0.00349 |
| Haiku 4.5 | $0.00004 | $0.00175 |
Grade A, and why
thinking-craftsman-skill 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 4d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking Craftsman Coding Skill
Thinking Craftsman coding skill defines the coding concepts and principles that apply across broad range of technologies and programming languages.
When to Invoke
- Invoke directly when: the user asks for a "thinking craftsman" review of a specific change, file, or PR.
- Invoke via:
/tcreview(single-perspective review) - Use the template defined in
references\templates.mdas per the task type - Use the language specific information from
references\<language>.mde.g.references\python.mdfor information specific to python language, C++ usereferences\cpp.md
When and How to Apply
Apply these guidelines during agentic code generation and during code review.
Enforcement Levels
- Mandatory
- Treat these as hard constraints by default.
- Violate them only when the user explicitly asks for a tradeoff or the target codebase has an established conflicting convention.
- If a mandatory rule cannot be followed, explain the reason clearly.
- Preferred
- Treat these as strong defaults.
- They guide design and implementation, but they may be relaxed with justification.
- During review, call out deviations as design risks, not automatic failures.
- Review Only
- Use these as review prompts and inspection checks.
- Do not block code generation on these alone unless they expose a concrete defect, regression, or architectural problem.
There are two scopes of guidelines.
- File or class scope guidelines
- Function scope guidelines
Mandatory Rules
Mandatory File or Class Scope Rules
- Respect module boundaries and layering
- Do not move files unless explicitly instructed.
- Keep configuration separate from runtime logic.
- Avoid circular dependencies.
- Do not generate code that violates Liskov Substitution Principle (LSP)
- If a class derives from another class, analyze the assumptions of the base class before changing derived behavior.
- Where function names are the same in base and derived classes, assume the derived function overrides the base function.
- Preconditions of the derived method must be no stricter than the base method.
- Postconditions of the derived method must be at least as strong as the base method.
- If the preconditions or postconditions are unclear, ask the user to verify them.
- Handle errors and exceptions without suppressing them
- Do not swallow exceptions silently.
- Do not create empty catch blocks.
- Catch specific exception types instead of the language's root exception type.
- Do not catch catch-all forms such as
.... - Catch exceptions as late as practical, usually in higher-level public entry points.
- Read the relevant task context before generating or reviewing code
- Read the spec, task description, and relevant code comments before making changes.
- If you are uncertain about something, say so and suggest investigation rather than guessing.
What ships with it
6 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.
- 4d ago First seen · 158 lines · 42 tokens per session scan A 3d110073fe32
thinking-craftsman-skill is a skill published in the GitHub repository nitinbhide/tcaitoolkit (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 42 tokens to every session and 1,747 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
azure-mgmt-apicenter-dotnet
Azure API Center SDK for .NET. Centralized API inventory management with governance, versioning, and discovery. Use for creating API services, workspaces, APIs, versions, definitions, environments, deployments, and metadata schemas. Triggers: "API Center", "ApiCenterService", "ApiCenterWorkspace", "ApiCenterApi", "API…
azsdk-common-pipeline-analysis
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdkanalyzepipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in…
requirements-author
Requirements authoring guide for BRD and PRD across Discover, Define, and Govern with canonical templates and handoff contracts.
mps-aspect-actions
Use when defining or editing MPS node factories (the "actions" aspect) — NodeFactories roots, per-concept NodeFactory setup functions that initialize a freshly created node and optionally copy data from a replaced sampleNode, plus the actions aspect's CopyPasteHandlers and PasteWrappers roots. Reach for this skill…
mps-aspect-intentions
Use when defining or editing MPS intentions (the Alt+Enter context-action aspect) — adding IntentionDeclaration roots, parameterized or surround-with variants, description/isApplicable/execute blocks, child-filter functions, factory-initialized AST splicing, or debugging why an intention is not offered. Lives in the…
marginfi
MarginFi — Solana lending and borrowing.