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/yourtechbud/coding-harness-config/authoring-skillsnpx skills add YourTechBud/coding-harness-config --skill authoring-skillsgit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWrote 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/yourtechbud/coding-harness-config/authoring-skills)<a href="https://agentmods.dev/skills/yourtechbud/coding-harness-config/authoring-skills"><img src="https://agentmods.dev/badge/skills/yourtechbud/coding-harness-config/authoring-skills.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 5.1 | $0.00018 | $0.00623 |
| Opus 5 | $0.00009 | $0.00311 |
| Sonnet 5 | $0.00004 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
authoring-skills 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 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.
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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authoring Skills
Author the skill now from the behavior, boundaries, and decisions already established in the conversation and any supplied specification.
User-supplied authoring request:
$ARGUMENTS
Treat the established decisions as the source of truth. Resolve details from the conversation, supplied materials, repository instructions, and target harness conventions before asking the user; ask only when a missing decision materially changes the skill and cannot be recovered from context.
Guidance
Before writing, read the current versions of these guides completely:
- Fable 5.1: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-fable-5-1
- GPT 6: https://developers.openai.com/api/docs/guides/latest-model?model=gpt-6-astra
Follow the applicable repository and harness instructions when they define the canonical source format, supported metadata, invocation policy, resource layout, or validation command.
Authoring Standard
- Encode the intended behavior, outcome, decision boundaries, required evidence, and completion criteria. Prescribe a process only when its order or mechanics materially affect the result.
- Trust the model to choose among valid approaches. Match specificity to fragility: use exact instructions for invariants and failure-prone operations, and leave contextual judgment open.
- Make every instruction earn its context. Audit each sentence in isolation for a behavioral change relative to the target model's default, and delete the whole sentence when it is a no-op.
- Phrase the desired behavior positively. Use a prohibition only for a genuine guardrail that cannot be expressed positively, and pair it with the behavior to follow instead.
- Keep each meaning in one authoritative place. Treat repository files, tool help, and target specifications as sources of truth; point to them when lookup is cheap instead of copying facts that can drift.
- Add examples, scripts, references, assets, or auxiliary metadata only when they materially improve behavior, reliability, or discovery.
- Write the description for the intended invocation policy. For model-invoked skills, state what the skill does and the distinct contexts that should trigger it without padding the description with synonymous triggers or body content; for explicit-only skills, use a concise human-facing summary.
- Keep conditional detail behind direct, condition-bearing pointers. Inline material every invocation needs.
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 Changed · -1 lines 58c44210c1e0
- 6d ago First seen · 44 lines · 18 tokens per session scan A bffed8c8e4a1
authoring-skills is a skill published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 18 tokens to every session and 623 once invoked, about $0.0001 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…
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…
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…
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…