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 skills add jtsang4/efficient-coding --skill problem-framinggit clone --depth 1 https://github.com/jtsang4/efficient-codingWrote 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/jtsang4/efficient-coding/problem-framing)<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/problem-framing"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/problem-framing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jtsang4/efficient-coding/problem-framing"><img src="https://agentmods.dev/badge/skills/jtsang4/efficient-coding/problem-framing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00581 |
| Opus 5.5 | $0.00024 | $0.00232 |
| Sonnet 5.5 | $0.00012 | $0.00116 |
| Haiku 4.5 | $0.00006 | $0.00058 |
Grade A, and why
problem-framing 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 1mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Problem framing
Treat rising complexity and repeated non-convergence as diagnostic signals that the problem may be framed incorrectly. They are evidence to investigate, not proof that the requirement is false.
Pause refinement of the disputed design long enough to examine the problem it serves. Use the conversation and available artifacts before asking the user to repeat information.
Diagnose and reframe
- Identify the signal concretely: which branches, exceptions, or layers keep appearing, or which point keeps being re-argued without new evidence?
- Restate the intended outcome independently of the proposed implementation. Identify who needs it and what observable result would count as success.
- Separate established requirements from assumptions and implementation choices. Check the evidence behind the requirement driving the complexity. Mark unsupported claims as unverified, not false. Preserve confirmed constraints, including compatibility, safety, and business obligations.
- Name the suspected false problem explicitly. State which assumption may be manufacturing the difficulty and why. Consider whether the actual cause is missing information, conflicting requirements, or unavoidable domain complexity instead.
- Offer a simpler framing tied to the same intended outcome. Explain exactly which complexity would disappear and which tradeoffs or constraints remain. A proposal that quietly drops a real requirement is not a successful reframing.
- Identify the smallest check that can distinguish the original framing from the alternative. Use available evidence or a reversible experiment where practical; ask a focused question only when necessary information is missing.
Communicate the decision
Tell the user plainly, in their language:
- The observed complexity or loop.
- The intended outcome and the assumption being questioned.
- The suspected false problem and proposed reframing.
- The evidence or check needed, followed by a recommended next step.
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.
- 1mo ago First seen · 37 lines · 59 tokens per session scan A 95d9b2e512b1
problem-framing is a skill published in the GitHub repository jtsang4/efficient-coding (2 stars, last pushed 8d ago), licensed MIT. It adds 59 tokens to every session and 581 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-10.
Other skills, from other repositories
plugin-creator
Create and scaffold plugin directories for Codex with a required .codex-plugin/plugin.json, optional plugin folders/files, valid manifest defaults, and personal-marketplace entries by default. Use when Codex needs to create a new personal plugin, add optional plugin structure, generate or update marketplace entries…
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.