lore-oss: Skill for Claude Code

.claude/skills/lore-feature/SKILL.md

lore-feature is a skill for Claude Code from re-cinq/lore-oss. It costs 39 tokens per session (860 once invoked), scanned A, original, Apache-2.0.

An interactive workflow for implementing a software feature from a written specification, or creating that specification when one does not exist. It breaks the work into a plan and tasks, then guides implementation.

In plain words
What is it for?
Use it to inspect existing feature specs, create new specs, define tasks, understand repository conventions, and work through implementation step by step.
Why use it?
It gives developers a consistent path from an idea or request to reviewed, trackable code changes.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is re-cinq/lore-oss's own configuration. It tells Claude Code how to work on lore-oss 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 lore-oss configures →

Reuse

Borrowing it

Nothing to install: this file belongs to re-cinq/lore-oss. 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/re-cinq/lore-oss/main/.claude/skills/lore-feature/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/re-cinq/lore-oss

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 lore-feature

README.md
[![agentmods](https://agentmods.dev/badge/skills/re-cinq/lore-oss/lore-feature/github.svg)](https://agentmods.dev/skills/re-cinq/lore-oss/lore-feature)
Your own site
<a href="https://agentmods.dev/skills/re-cinq/lore-oss/lore-feature"><img src="https://agentmods.dev/badge/skills/re-cinq/lore-oss/lore-feature/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 lore-feature

Your own site · 80×15
<a href="https://agentmods.dev/skills/re-cinq/lore-oss/lore-feature"><img src="https://agentmods.dev/badge/skills/re-cinq/lore-oss/lore-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 860 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 $0.00039 $0.00860
Opus 5.5 $0.00016 $0.00344
Sonnet 5.5 $0.00008 $0.00172
Haiku 4.5 $0.00004 $0.00086

Measured 2mo ago against content hash 02860084359d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lore-feature 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 2mo 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.

.claude/skills/lore-feature/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are helping a developer implement a feature. Do the work yourself. Ask one question at a time. Run commands yourself. Wait for confirmation only at decision points.

Two entry points

Entry A: Feature already has a spec (PM created it via Lore)

  1. List available specs: ls specs/ and show them.
  2. Ask: "Which feature do you want to work on?" (or they already told you)
  3. Read the spec: specs/{feature}/spec.md
  4. Read the tasks: specs/{feature}/tasks.md (if exists)
  5. Read the data model: specs/{feature}/data-model.md (if exists)
  6. Show a summary: what the feature does, how many tasks, which are done.
  7. Ask: "Ready to start? I'll work through the tasks in order."

Entry B: New feature (no spec yet)

  1. Ask: "What do you want to build? Short description — what and why."
  2. Load repo context via get_context (Lore MCP) to understand conventions.
  3. Create the feature directory: specs/{slug}/
  4. Write specs/{slug}/spec.md — problem statement, user scenarios, functional requirements, success criteria. Match the style of existing specs in this repo.
  5. Show the spec. Ask: "Does this capture what you want?"
  6. Write specs/{slug}/tasks.md — checklist format:
    - [ ] T001 [P] Description with file path
    - [ ] T002 Description with file path
    
    Organized by phase. Mark parallelizable tasks with [P]. Include actual file paths from the repo structure.
  7. Show the tasks. Ask: "Does this breakdown look right?"
  8. Commit the spec files: git add specs/{slug}/ && git commit

Implementation flow (both entry points)

Once the spec and tasks exist:

  1. Create a feature branch: git checkout -b feat/{slug}
  2. Find the first uncompleted task in tasks.md
  3. Show: "Working on T{N}: {description}"
  4. Implement the task — write code, create files, modify existing code. Follow the repo's conventions from CLAUDE.md.
  5. After completing the task, mark it done in tasks.md: Change - [ ] T{N} to - [x] T{N}
  6. Commit the changes with a clear message referencing the task.
  7. Ask: "T{N} done. Continue to T{N+1}?" (or let them review first)
  8. Repeat until all tasks are done or developer stops.

Read the full file on GitHub · 78 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. 2mo ago First seen · 78 lines · 39 tokens per session scan A 02860084359d

Subscribe to this mod's changes

lore-feature is a skill published in the GitHub repository re-cinq/lore-oss (12 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 860 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.

Related

lore-feature compared with skills from other repositories

lore-feature next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lore-featurere-cinq/lore-ossSkill127mo agoApache-2.0A39Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code