A command that asks an agent to extract the existing behavioral rules of a codebase into OpenSpec specification files. OpenSpec is a structured place for documenting what software must do, especially when adopting specification-driven development.

Use it to mine requirements and invariants from a project or module and save them under its OpenSpec specifications directory.

It turns undocumented behavior in an older project into a written baseline before later changes rely on it.

spec-mine — Command for Claude Code by hmj1026: A command that asks an agent to extract the…

Install

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.

agentmods

npx agentmods add commands/hmj1026/dhpk/spec-mine

Clone the repo

git clone --depth 1 https://github.com/hmj1026/dhpk

Made for: Claude Code.

Or install dhpk, the plugin that ships this one along with the rest of its 65 skills, 31 commands, 40 agents, 4 hooks.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/hmj1026/dhpk/spec-mine.svg)](https://agentmods.dev/commands/hmj1026/dhpk/spec-mine)

Your own site

<a href="https://agentmods.dev/commands/hmj1026/dhpk/spec-mine"><img src="https://agentmods.dev/badge/commands/hmj1026/dhpk/spec-mine.svg" alt="Measured on agentmods" height="20"></a>

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 532 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00033	$0.00532
Opus 5	$0.00016	$0.00266
Sonnet 5	$0.00007	$0.00106
Haiku 4.5	$0.00003	$0.00053

Measured today against content hash 4bc6084d4715, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

spec-mine 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 today.

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.

commands/spec-mine.md · 34 lines

What it actually says

/spec-mine

Front door for behavioral-spec extraction. This command does not mine inline — it dispatches the spec-miner agent (opus), which owns the sampling budget, metadata rules, and the flat Requirement / Invariant output format. Mirrors how the Playwright route delegates journeys directly to the agent:e2e-runner capability (an unavailable browser/agent is reported as UNAVAILABLE, not remapped to another test workflow).

When to use

Onboarding an existing project to spec-driven development ("mine specs", "extract specs from the codebase", "萃取規格").
A module's existing behavior needs documenting as OpenSpec baseline truth before opsx-apply-goal / /opsx:apply changes can reference it.

Steps

Pre-flight — confirm this is (or should be) an OpenSpec project:
```
ls openspec/specs 2>/dev/null && echo "specs dir present" || echo "no openspec/specs yet"
```
If openspec/ is absent, ask before creating it — spec-miner never scatters spec files outside openspec/specs/.
Dispatch the spec-miner agent via the Agent tool (subagent_type: dhpk:spec-miner), passing $ARGUMENTS (the capability or path to mine first; omit to let the agent present the capability list and ask).
Relay the agent's result: the written openspec/specs/<capability>/spec.md path, the capability name, the Last verified commit stamp, and any  files to schedule for a follow-up pass.

Constraints

The deliverable is openspec/specs/<capability>/spec.md (the agent's only Write target) — not a .claude/artifacts/ report.
Do not mine every module at once; mine the requested capability (or ask which one first). Spec rot starts when specs outpace usage.

$ARGUMENTS: optional capability name or path to mine first.

Changes

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.

today First seen · 34 lines · 33 tokens per session scan A 4bc6084d4715

Subscribe to this mod's changes

spec-mine is a command published in the GitHub repository hmj1026/dhpk (2 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 532 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 2026-09-05.

OpenSpec Planning ai-tooling claude-code claude-code-plugin harness

spec-mine

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

/spec-mine

When to use

Steps

Constraints

What this file has done since we first saw it

Other commands, from other repositories

init

spec

debug

review

review

config