agentmods.dev

claude-context: Skill for Claude Code

.agents/skills/spec-discovery/SKILL.md

spec-discovery is a skill for Claude Code from lbruton/claude-context. It costs 38 tokens per session (728 once invoked), scanned A, original, MIT.

A post-merge Git cleanup workflow. Git is the version-control system used to track code changes, branches, and separate working directories called worktrees.

In plain words
What is it for?
Use it after merging a pull request to prune remote references, delete merged local branches and worktrees, update the main branch, and report the result.
Why use it?
Merged branches and stale worktrees can clutter a repository and leave outdated remote references. This workflow removes that leftover state and checks whether anything still needs cleaning.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is lbruton/claude-context's own configuration. It tells Claude Code how to work on claude-context itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-context configures →

not rated 2repo +1 changed 5d ago A scan 38 tokens original MIT
View source ↗ lbruton/claude-context
Reuse

Borrowing it

Nothing to install: this file belongs to lbruton/claude-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lbruton/claude-context/master/.agents/skills/spec-discovery/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/lbruton/claude-context

Made for: Claude Code.

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.

agentmods badge for spec-discovery

README.md
[![agentmods](https://agentmods.dev/badge/skills/lbruton/claude-context/spec-discovery/github.svg)](https://agentmods.dev/skills/lbruton/claude-context/spec-discovery)
Your own site
<a href="https://agentmods.dev/skills/lbruton/claude-context/spec-discovery"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/spec-discovery/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.

agentmods 80×15 button for spec-discovery

Your own site · 80×15
<a href="https://agentmods.dev/skills/lbruton/claude-context/spec-discovery"><img src="https://agentmods.dev/badge/skills/lbruton/claude-context/spec-discovery.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00728
Opus 5.5 $0.00015 $0.00291
Sonnet 5.5 $0.00008 $0.00146
Haiku 4.5 $0.00004 $0.00073

Measured 5d ago against content hash b9ce1a4e845a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

spec-discovery 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.

.agents/skills/spec-discovery/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/spec-discovery ISSUE

Phase 2: research what already exists and what's unknown, into discovery.md. One artifact, then STOP.

Invocation

/spec-discovery <ISSUE-ID>

Missing <ISSUE-ID> → print Usage: /spec-discovery <ISSUE-ID> and exit.

Read first — shared conventions

Read .agents/skills/spec/references/conventions.md and the project's .context/spec-conventions.md if present. They define folder resolution, phase-boundary discipline, and the unreconciled-marks pre-check used below.

Steps

  1. Resolve the spec folder per conventions.md. Read requirements.md first — it's the input.

  2. Unreconciled-marks PRE-CHECK (per conventions.md): scan requirements.md for reviewer marks outside ## Review Archive. If any exist, STOP: "requirements has not been reconciled — run /spec-reconcile {ISSUE-ID} requirements first." Do not research on top of un-reconciled review.

  3. Research sweep — four read-only angles. Default to inline research. If the user explicitly asks for parallel agents, use read-only explorer subagents for independent angles. Subagents never edit files.

    • Structural — Grep/Glob for affected modules, callers, dependencies. Grep each candidate identifier repo-wide and read the hits; that is the exhaustive path to a call list.
    • Semantic — claude-context search_code for the feature domain, reusable patterns, integration points.
    • Prior decisions — mem0 (and sessionflow if useful) for past choices on this area. Record exact query strings.
    • External — context7 / Brave for libraries, RFCs, platform docs — only if the work involves them.

    Synthesize the returned findings yourself; do not let an agent write discovery.md. For a narrow spec where one or two angles obviously suffice, skip the Workflow and run those searches inline — match the fan-out to the surface area.

  4. Draft discovery.md per the template:

    • Existing code/files relevant to the work (with path:line).
    • Prior decisions (mem0/sessionflow) — cite the query strings used.
    • External references (libraries, RFCs, docs) with links.
    • Open questions that block approach.md.

  5. Save discovery.md. Touch no other file.

Read the full file on GitHub · 59 lines

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.

  1. 5d ago Changed b9ce1a4e845a
  2. 9d ago Changed 708a0396f9b8
  3. 11d ago First seen · 59 lines · 38 tokens per session scan A 8a3493a14987

Subscribe to this mod's changes

spec-discovery is a skill published in the GitHub repository lbruton/claude-context (2 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 728 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 2026-10-17.

Git and workflow
Related

Other skills, from other repositories

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 tokens

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

release-helper

Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.

Sahir619/fable-method · 43 tokens