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/shaping-issuesnpx skills add YourTechBud/coding-harness-config --skill shaping-issuesgit clone --depth 1 https://github.com/YourTechBud/coding-harness-configWhat 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 | $0.00086 | $0.00945 |
| Opus 5 | $0.00043 | $0.00473 |
| Sonnet 5 | $0.00017 | $0.00189 |
| Haiku 4.5 | $0.00009 | $0.00094 |
Grade A, and why
shaping-issues 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shaping Issues
Role
Shape and reshape product epics and their stories from raw Sparks and project context. Pair this domain model with the brainstorming skill, which supplies the questioning, research, pushback, and shared-understanding process.
Epics and stories preserve the product understanding that future humans and agents need. Detailed engineering decisions belong to later story-level brainstorming and, when useful, a temporary implementation plan.
Shared Terms
- Spark: raw input such as an idea, pain, bug, feature notion, observation, or unfinished thread. Sparks are processed into epic understanding or remain raw for later.
- Epic: a mostly stable, product-oriented account of the valuable promise currently being pursued, its context, its scope, and what would make it complete.
- Candidate epic: an uncommitted seed for a direction that may become valuable later. It preserves enough context to resume shaping without treating today's understanding as settled.
- Story: a disposable, acceptance-oriented increment under one epic. A story preserves enough product context to seed later brainstorming while leaving its engineering path open.
- Acceptance criteria: observable conditions used to judge whether a story achieved its outcome.
Every story belongs to one epic, and the persistence representation must make navigation possible in both directions. Every story has exactly one kind:
- Exploration: reduces consequential uncertainty and applies its conclusions to the epic or downstream stories.
- Implementation: delivers a coherent valuable outcome that satisfies its acceptance criteria.
- Release: handles an exceptional external transition whose coordination, judgment, or risk requires direct human-agent work.
Shaping Phases
Give each shaping phase its own focused user turn. Surface the phase's working understanding, apply the relevant pushback, and invite the user to correct or deepen it. Advance after the user can meaningfully confirm or edit the phase's completion criterion, then make the phase change visible.
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.
- 2d ago First seen · 55 lines · 86 tokens per session scan A 613141c76c92
shaping-issues is a skill published in the GitHub repository YourTechBud/coding-harness-config (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 86 tokens to every session and 945 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…