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 OutlineDriven/outline-driven-development --skill exploregit clone --depth 1 https://github.com/OutlineDriven/outline-driven-developmentWrote 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/outlinedriven/outline-driven-development/explore)<a href="https://agentmods.dev/skills/outlinedriven/outline-driven-development/explore"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/explore/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/outlinedriven/outline-driven-development/explore"><img src="https://agentmods.dev/badge/skills/outlinedriven/outline-driven-development/explore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00040 | $0.00995 |
| Opus 5 | $0.00020 | $0.00498 |
| Sonnet 5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
explore 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.
How it starts
The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explore
Contract
| Field | Bound contract |
|---|---|
| Trigger | User says "explore", "find where X is", "how does X work in the code", or "map the codebase" for repo-local orientation. |
| Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. |
| Side effect | A structured orientation report in chat; may dispatch Explore subagents. No state mutation. |
| Done | All 8 output sections emitted or applicability stated, scope declared, and dispatch/escalation rules followed. |
Inputs
- Task text (supplied): the orientation question or concern to map.
- Repo working tree (supplied by environment): read-only access to the local checkout.
- Optional: specific files, directories, or concerns used to bound scope before dispatch.
Procedure
- Scope. Parse the task; identify the files, directories, and concerns in scope. State the scope explicitly before any dispatch or read. Done when: the scope is stated explicitly before any dispatch or read.
- Dispatch decision. For multi-file or uncertain tasks, dispatch Explore subagents instead of reading directly. Escalation: 1 subagent for a single-concern known scope; 3 subagents for multiple concerns or unknown scope; 5 subagents for a cross-module or architectural survey. Auto-skip (direct reads allowed) only for a single file under 50 LOC. Dispatch first; do not grep or glob a multi-file task before dispatching. Done when: the dispatch decision is made with the correct escalation tier, or direct reads are selected for a single file under 50 LOC.
- Discovery with token-efficient flags. File discovery:
fd -e <ext> --max-results 50. Symbol search:ast-grep run -p 'PATTERN' -l <lang> -C 1orgit --no-pager grep -n -C 2 'pattern'. Content preview:bat -P -p -n -r START:END fileor read with offset/limit. Directory structure:eza --tree --level=2. Done when: discovery is completed using token-efficient flags. - Synthesis. Emit all 8 output sections below. Omit a section only when genuinely not applicable and state why. Done when: all 8 output sections are emitted or omitted with a stated reason.
- Heavy-codebase escape hatch. When scope exceeds 50 files, use a codebase-packing tool only as an internal analysis aid; never give packed output to the user. Search the packed output for targeted extraction. If no packing tool is available, narrow scope and state the narrowing. Done when: the heavy-codebase escape hatch is applied or scope is narrowed with a stated reason.
- Tool restrictions. Allowed (read-only):
eza,fd,ast-grep(find-only),git grep,rg,bat,tokei,Read,codebase_search, and any available codebase-analysis or codebase-packing MCP tooling. Banned:Edit,Write,mcp__edit__edit_file,git commit, and any state-mutating bash command. Done when: only allowed tools are used and no banned tool is invoked. - Recursion guard. Do not re-enter a router or orchestrator skill from within this leaf skill. Done when: no router or orchestrator skill is re-entered.
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.
- 5d ago First seen · 42 lines · 40 tokens per session scan A 2ccf516f1cba
explore is a skill published in the GitHub repository OutlineDriven/outline-driven-development (52 stars, last pushed 3d ago), licensed Apache-2.0. It adds 40 tokens to every session and 995 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
slicing-code-context
Use when an exact symbol, path, entrypoint, or line range can bound a focused code question or patch proposal under a fixed source budget. Not for source changes or broad repository exploration.
askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via /askme.
handoff-prompt
Use when the user asks for a handoff, delegation, or clipboard-ready prompt for another agent: a standalone path-free prompt copied to the clipboard, confirmed by title. Not for session-snapshot briefs — use handoff; never remote, credential, publish, deploy, or irreversible.
autopilot
Run a hands-off plan-to-ship pipeline by chaining existing skills. Use when the user says "autopilot", "take this from plan to shipped", "run the whole pipeline", "hands-off ship it", or "do the end-to-end build".
llm-self-loop
Use when a button click, dashboard check, or human verdict sits inside an iteration loop. Replaces it with an autonomous gate or moves non-automatable work outside the loop. Don't use for remote, credential, publish, deploy, or irreversible changes.
catchup
Use when the human returns after a gap, cannot follow the project, asks what happened, or wants a visual HTML recap page. Not for onboarding: use onboard. Not for handoff: use handoff.