devkit-api-change
Trace and verify every consumer before changing a public signature in src/devkit/ (env.py, db.py, oauth.py, mcpsecurity.py, mcpserver/, bridge/, bootstrap.py).
Skill by rahulc810
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/rahulc810-devkit-api-change
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/devkit-api-change
Tools it pre-approves 4
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Grep,Glob,Bash
What's inside
- Skill name
devkit-api-change- Description
- Trace and verify every consumer before changing a public signature in src/devkit/ (env.py, db.py, oauth.py, mcpsecurity.py, mcpserver/, bridge/, bootstrap.py). Use when renaming, adding or removing a parameter, changing a default or return type, moving a symbol between modules, or when asked "what breaks if I change this".
- License
- unknown
- Allowed tools
- Read,, Grep,, Glob,, Bash
- Instructions
- 75 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves any shell command
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from rahulc810/claude_settings
- 0.559score
code-review
rahulc810
Review a diff, a plan's implementation, or a plan before execution, for correctness, quality and plan adherence, bucketing findings by severity into…
SkillAFreshness: AClaude Code +9 - 0.559score
designit
rahulc810
Iteratively drill a feature, idea or requirement into a locked spec, then hand it to /plan-doc.
SkillAFreshness: AClaude Code +9 - 0.559score
plan-doc
rahulc810
Translate a spec into a numbered, deterministic implementation plan under specs/.
SkillAFreshness: AClaude Code +9 - 0.555score
observer
rahulc810
Audit the setup as it is actually used — session transcripts, skill/agent/MCP invocation counts, session shape, round-trip waste — and report ranked findings…
SkillAFreshness: AClaude Code +9 - 0.519score
finalize
rahulc810
Prepare a branch for merge — done-checks, pre-merge docs, version bump, then a staged conventional commit.
SkillBFreshness: BClaude Code +9 - 0.519score
implement
rahulc810
Execute a specs/ plan end to end, one step at a time, then hand off to finalize.
SkillBFreshness: BClaude Code +9 - 0.519score
improve
rahulc810
Scan the code against four architecture checks — layout, isolation, interface strength, extensibility — and propose specific fixes without applying them.
SkillBFreshness: BClaude Code +9 - 0.519score
land-feature
rahulc810
Devkit overlay on /finalize — append the COMPLETE_ACTIONS.md entry and reconcile CLAUDE.md invariants for repos that use that ledger contract.
SkillBFreshness: BClaude Code +9 - 0.519score
notice
rahulc810
Note a recurring friction, correction, or workflow pattern during work, for later review as a possible new or improved skill.
SkillBFreshness: BClaude Code +9 - 0.519score
crawl
rahulc810
Explore a codebase and write or update a dense, factual CODEBASE.md context document for other skills to consume.
SkillBFreshness: BClaude Code +9 - 0.519score
forge
rahulc810
Take raw idea notes and adversarially decide whether each should become a skill — fold into an existing one, add as new, or drop — with an in-principle rating.
SkillBFreshness: BClaude Code +9 - 0.519score
distill
rahulc810
Compress material into judgment instead of coverage — what a skim would miss, then the three or four points to lead with.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 2, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/rahulc810/claude_settings
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from rahulc810
- 0.559score
plan-doc
rahulc810
Translate a spec into a numbered, deterministic implementation plan under specs/.
SkillAFreshness: AClaude Code +9 - 0.559score
designit
rahulc810
Iteratively drill a feature, idea or requirement into a locked spec, then hand it to /plan-doc.
SkillAFreshness: AClaude Code +9 - 0.559score
code-review
rahulc810
Review a diff, a plan's implementation, or a plan before execution, for correctness, quality and plan adherence, bucketing findings by severity into…
SkillAFreshness: AClaude Code +9 - 0.555score
observer
rahulc810
Audit the setup as it is actually used — session transcripts, skill/agent/MCP invocation counts, session shape, round-trip waste — and report ranked findings…
SkillAFreshness: AClaude Code +9 - 0.519score
implement
rahulc810
Execute a specs/ plan end to end, one step at a time, then hand off to finalize.
SkillBFreshness: BClaude Code +9 - 0.519score
forge
rahulc810
Take raw idea notes and adversarially decide whether each should become a skill — fold into an existing one, add as new, or drop — with an in-principle rating.
SkillBFreshness: BClaude Code +9
Cite this page
devkit-api-change skill. Agent Mart. https://agentmart.dev/skills/rahulc810-devkit-api-change (last updated 2026-10-24)