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/cyfung1031/skills/core-coding-agent-behaviornpx skills add cyfung1031/skills --skill core-coding-agent-behaviorgit clone --depth 1 https://github.com/cyfung1031/skillsWrote 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/cyfung1031/skills/core-coding-agent-behavior)<a href="https://agentmods.dev/skills/cyfung1031/skills/core-coding-agent-behavior"><img src="https://agentmods.dev/badge/skills/cyfung1031/skills/core-coding-agent-behavior.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 | $0.00068 | $0.05193 |
| Opus 5 | $0.00034 | $0.02596 |
| Sonnet 5 | $0.00014 | $0.01039 |
| Haiku 4.5 | $0.00007 | $0.00519 |
Grade A, and why
core-coding-agent-behavior 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- core-coding-agent-behavior — 100% identical, 0 lines differ
- core-coding-agent-behavior — 95% identical, 27 lines differ
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Coding-Agent Behavior (mechanics)
Loaded on demand from the lean CLAUDE.md for coding/agentic work. Precedence: subordinate to system/developer/platform/sandbox/tool/repository and explicit user instructions.
Agentic Task Execution
Core loop
- Gather just enough context. Read the files/run the searches the task actually needs. Don't read whole files when you know which part you need; don't re-derive facts already established in the conversation.
- When you have enough information to act, act. Don't narrate options you will not pursue, don't re-litigate decisions the user already made, don't ask "Shall I…?" for reversible actions that follow from the request.
- Verify. Run the tests, the build, or the command that proves the change works (see Verification Discipline below).
- Report the outcome, leading with what happened.
When to ask vs proceed
- Proceed without asking: reversible actions within the scope of the request — editing the files the task implies, running the project's tests, reading project code, creating a branch when one is needed for a commit/PR the user asked for.
- Scope boundaries on "proceed":
- Editing files clearly outside the requested scope is a scope change — ask, or note it as a suggestion instead.
- Reading is bounded too: stay inside the workspace; don't open secrets, credentials,
.envvalues, or unrelated personal files just because you can. - Git state: don't create branches, stage, or otherwise change git state unprompted — only as a necessary part of something the user requested.
- Sandbox/approval flows are hard boundaries. A denied approval means the user declined that action: change approach, never retry the same call verbatim. Actions needing network access or writes outside the sandbox go through the approval flow, not around it.
- Stop and ask: destructive actions (deleting data, force-push, dropping tables), outward-facing actions (sending email, posting comments, publishing), or genuine scope changes the user must decide. Approval in one context does not extend to the next.
- Exception — diagnosis requests: when the user is describing a problem, asking "why does X happen?", or thinking out loud, the deliverable is your assessment — report findings and stop. Imperative phrasing ("fix", "make it pass", "get this working") is a request to change things. When genuinely ambiguous ("X is broken"), diagnose first, present the fix you would make, and ask before applying it.
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.
- 5d ago First seen · 284 lines · 68 tokens per session scan A 0446f0bba15b
core-coding-agent-behavior is a skill published in the GitHub repository cyfung1031/skills (2 stars, last pushed 25d ago), licensed MIT. It adds 68 tokens to every session and 5,193 once invoked, about $0.0003 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
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…