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 pivoshenko/pivoshenko.ai --skill spec-exploregit clone --depth 1 https://github.com/pivoshenko/pivoshenko.aiWrote 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/pivoshenko/pivoshenko.ai/spec-explore)<a href="https://agentmods.dev/skills/pivoshenko/pivoshenko.ai/spec-explore"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/spec-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/pivoshenko/pivoshenko.ai/spec-explore"><img src="https://agentmods.dev/badge/skills/pivoshenko/pivoshenko.ai/spec-explore.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 | $0.00242 | $0.01773 |
| Opus 5.5 | $0.00097 | $0.00709 |
| Sonnet 5.5 | $0.00048 | $0.00355 |
| Haiku 4.5 | $0.00024 | $0.00177 |
Grade A, and why
spec-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 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Explore
question -> read the codebase -> converge -> hand to spec-propose.
Explore writes nothing. No artifact, no branch, no commit, no source edit, not even a scratch file in the repo. Why -> an explore that edits leaves the tree holding a change nobody proposed and no spec describes, so the next stage either commits work it never planned or spends its first move reverting yours.
Flow
- Preflight.
openspec context --json.no_openspec_root-> say so once and keep going. Exploring is read-only and needs noopenspec/. Do not offeropenspec init --tools claudeyet, and never run it unasked. User names a store ->openspec store list --jsonfor ids, then--store <id>on every later call, sticky for the run - Delegate the mechanics.
.claude/commands/opsx/explore.mdexists -> that command owns explore mode, invoke it, and keep only the framing, the question discipline, and the handoff for yourself. Absent -> drive the discovery yourself per Grounding - Ground first. See Grounding. Read before a single question reaches the user - every factual question you could answer by reading, read
- Restate the question in one line, carrying what you read - the module it lands in, the file that already does the nearest thing, or the thing that turns out not to exist at all. State the framing and move straight into the first question. It is a frame, never a confirmation gate, so nothing waits on it; a wrong premise gets corrected here at the cost of one line rather than the session. Why -> a restatement offered before reading can only echo the user's own words back, which costs a full turn and returns nothing they did not already know, and it breaks Grounding's own rule never to ask what you can read
- Ask one question at a time. See Questions
- Check the existing specs for collisions. See Collisions
- Converge and hand off. See Convergence. Root exists ->
spec-propose. Root missing -> now offeropenspec init --tools claude, wait for the user, thenspec-propose
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 · 101 lines · 242 tokens per session scan A e710cec5b919
spec-explore is a skill published in the GitHub repository pivoshenko/pivoshenko.ai (6 stars, last pushed yesterday), licensed MIT. It adds 242 tokens to every session and 1,773 once invoked, about $0.0010 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 2026-09-16.
Other skills, from other repositories
comet-archive
A workflow for the fifth stage of Comet Classic: archiving a completed change, merging its specification updates, and finishing the branch. It uses Comet commands and a fixed layout for tracking the change.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.
comet-archive
Comet Phase 5: Archive. Invoke with /comet-archive. Merge delta specs into main specs with OpenSpec semantics, archive change.
comet-github-pr-review
A read-only review process for pull requests in Comet's GitHub repositories. A pull request is a proposed code change; the review checks its current code, related issue, comments, merge status, and automated checks.
comet-release
A release-preparation workflow for Comet that uses the real version, branch history, and user-visible changes to prepare a changelog and release checks. A changelog is a dated record of what changed for people using the software.