docsector-reader: Skill for Claude Code

.github/skills/docsector-feature-development/SKILL.md

docsector-feature-development is a skill for Claude Code from docsector/docsector-reader. It costs 58 tokens per session (707 once invoked), scanned A, original, MIT.

A development procedure for adding or changing features in Docsector, a documentation system. It covers environment inspection, clarification of uncertain requirements, regression tests, and related README updates.

In plain words
What is it for?
Use it when implementing or evolving Docsector functionality that needs code changes, tests, and documentation updates.
Why use it?
It reduces the risk of changing the wrong code path or leaving existing behavior untested. It also requires the final change to be validated or for any validation limits to be recorded.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is docsector/docsector-reader's own configuration. It tells Claude Code how to work on docsector-reader 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 docsector-reader configures →

Reuse

Borrowing it

Nothing to install: this file belongs to docsector/docsector-reader. 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/docsector/docsector-reader/main/.github/skills/docsector-feature-development/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/docsector/docsector-reader

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 docsector-feature-development

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/docsector/docsector-reader/docsector-feature-development"><img src="https://agentmods.dev/badge/skills/docsector/docsector-reader/docsector-feature-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 707 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 $0.00058 $0.00707
Opus 5.5 $0.00023 $0.00283
Sonnet 5.5 $0.00012 $0.00141
Haiku 4.5 $0.00006 $0.00071

Measured 2mo ago against content hash 295de06ddc96, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docsector-feature-development 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.

.github/skills/docsector-feature-development/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docsector Feature Development

When to Use

  • Create a new feature in Docsector.
  • Evolve existing behavior with functional impact.
  • Deliver a change that needs regression coverage and documentation updates.

Expected Outcome

  • The relevant environment was mapped before implementation.
  • Blocking questions were clarified, or non-blocking assumptions were made explicit.
  • The feature is covered by regression tests in the narrowest possible scope.
  • README.md is updated in the related section.
  • Executable validation was run for the change, or a limitation was documented.

Procedure

  1. Map the environment.

    • Find the nearest code path that actually decides the feature behavior.
    • Identify relevant files, components, composables, stores, routes, existing tests, and the potentially affected README.md section.
    • Form a local hypothesis: where the change belongs, which test can discriminate the expected behavior, and which narrow validation should be used.
  2. Ask when in doubt.

    • If there is ambiguity about expected behavior, scope, naming, user experience, compatibility, or which README section must be updated, ask before editing.
    • Ask only the smallest set of genuinely blocking questions.
    • If the uncertainty is not blocking, proceed with the smallest reasonable assumption and record it in the final summary.
  3. Implement regression tests.

    • Write or adjust a test that would fail without the feature and validates the expected behavior once the feature is applied.
    • Prefer the narrowest possible test first: validate the touched slice before broader checks unless they are necessary.
    • After the first substantive edit, immediately run the corresponding focused validation.
  4. Implement the feature.

    • Make the smallest change needed to reach the desired behavior.
    • Fix the root cause instead of only working around the symptom.
    • Preserve Docsector's existing style and abstractions.
  5. Update README.md.

    • Find the section most closely related to the delivered feature.
    • Document what changed, when to use it, and any relevant impact for project consumers.
    • If there is no exact section, update the nearest canonical section and state that explicitly in the final summary.

Read the full file on GitHub · 68 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 · 68 lines · 58 tokens per session scan A 295de06ddc96

Subscribe to this mod's changes

docsector-feature-development is a skill published in the GitHub repository docsector/docsector-reader (21 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 707 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

docsector-feature-development compared with skills from other repositories

docsector-feature-development next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
docsector-feature-developmentdocsector/docsector-readerSkill211mo agoMITA58Claude Code
321-frameworks-spring-boot-testing-unit-testsjabrena/cursor-rules-examplesSkill22mo agoApache-2.0A84Claude Code, Codex
322-frameworks-spring-boot-testing-integration-testsjabrena/cursor-rules-examplesSkill22mo agoApache-2.0A51Claude Code, Codex
mem0-test-integrationmem0ai/mem0Skill68k2d agoApache-2.0A207Claude Code, Codex
prowler-test-apiprowler-cloud/prowlerSkill15kyesterdayApache-2.0A62Claude Code
python-sdkComposioHQ/composioSkill31kyesterdayMITA60Claude Code, Codex
convex-testopenclaw/clawhubSkill9.5kyesterdayMITA16Claude Code, Codex