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 dgk-dev/dgk-gpt --skill regit clone --depth 1 https://github.com/dgk-dev/dgk-gptWrote 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/dgk-dev/dgk-gpt/re)<a href="https://agentmods.dev/skills/dgk-dev/dgk-gpt/re"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/re/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/dgk-dev/dgk-gpt/re"><img src="https://agentmods.dev/badge/skills/dgk-dev/dgk-gpt/re.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 | $0.00048 | $0.00464 |
| Opus 5.5 | $0.00019 | $0.00186 |
| Sonnet 5.5 | $0.00010 | $0.00093 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
re 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.
What it actually says
Re
Use this as a light override, not a rigid workflow. Keep Codex's default orchestration and only add extra diligence where it matters.
Defaults
- Inspect the local codebase first.
- Do research in 3 passes when the task is genuinely research-heavy:
- Plan 3-6 sub-questions.
- Retrieve sources for each sub-question and follow 1-2 second-order leads when useful.
- Synthesize only after resolving conflicts and gaps that could change the conclusion.
- Use Context7 first for version-sensitive library or framework behavior.
- Use native
webfirst for current information. - Use Jina only when native
webis not enough for long pages, PDFs, or parallel page reads. - Only cite sources retrieved in the current workflow, and label any inference that is not directly supported by those sources.
- If sources conflict, state the conflict explicitly instead of averaging them into one answer.
- If a search result is empty, partial, or suspiciously narrow, retry with a broader query, alternate wording, or a second source before concluding there is no answer.
- Compare options only when there is a real tradeoff.
- Implement once the decision is clear.
- Run the smallest relevant verification commands before finishing.
Avoid
- Do not force phases.
- Do not produce long research reports unless the user asked for them or the task materially benefits.
- Do not ask extra questions if local context is already enough.
- Do not delegate work just because this skill is active.
Large Tasks
For long tasks, optional scratch notes can live in /tmp/re-research/<slug>/.
If useful, keep a short decisions.md with:
- key findings
- rejected options
- remaining risks
- pending verification
Finish
Keep the final response compressed:
- decision
- source-backed justification
- key sources or citations when they materially matter
- code or config changed
- tests run
- remaining unknowns
What ships with it
1 file 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.
- 1mo ago First seen · 53 lines · 48 tokens per session scan A 0c6e6013129a
re is a skill published in the GitHub repository dgk-dev/dgk-gpt (55 stars, last pushed 7mo ago), licensed MIT. It adds 48 tokens to every session and 464 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 2026-08-30.
Other skills, from other repositories
codex-multi-profile
Multi-workspace profile router, MCP server (.mcp.json) security auditor, and CLAUDE.md AGENTS.md instruction bridge for Claude Code and OpenAI Codex. Isolates Enterprise, Open-Source Maintainer, and Personal profiles across /.claude and /.codex, and provides a native workspace switcher for the Microsoft Store Codex…
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.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
refocusing
Use when a long-running agent may have lost the product outcome, when context was compacted, when work has crossed a major boundary, or when a fresh path-based trace is needed before the next consequential action. Not for fresh-session orientation, waking an idle seat, or checkpoints.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.