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.
npx agentmods add skills/anilcancakir/claude-code-plugins/executenpx skills add anilcancakir/claude-code-plugins --skill executegit clone --depth 1 https://github.com/anilcancakir/claude-code-pluginsWhat 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 | $0.00054 | $0.00629 |
| Opus 5 | $0.00027 | $0.00315 |
| Sonnet 5 | $0.00011 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
execute 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Execution Skill
Guidelines for executing implementation plans effectively.
Execution Principles
- Follow Exactly - Do what the plan says, nothing more
- Verify Always - Run verification after each task
- Track Progress - Update plan file continuously
- Ask When Stuck - Report blockers, don't guess
Execution Workflow
1. Load Plan
- Read plan from
.claude/plans/ - Validate structure and status
- Check prerequisites
- Identify resume point if partially complete
2. Pre-Execution Checks
- Plan status is "approved" or "in_progress"
- All dependencies available
- Test framework ready (for TDD)
3. Execute Tasks
For each task:
- Announce task start
- Execute action
- Run verification
- Update status
- Report result
4. Phase Transitions
- Summarize completed phase
- Run phase-level verification
- Ask user before continuing
Task Actions
Create
- Use Write tool for new files
- Follow project conventions
- Include all required code
Modify
- Use Edit tool for changes
- Prefer precise edits over rewrites
- If Serena available, use
replace_symbol_body()
Delete
- Confirm with user first
- Consider backup for significant files
Run
- Execute via Bash tool
- Capture and report output
- Check exit code
Verification Patterns
# Command verification
[command] && echo "PASSED" || echo "FAILED"
# File verification
test -f [path] && echo "File exists"
# Test verification
php artisan test --filter=[Test]
flutter test [file]
npm run test -- [file]
Error Handling
Task Failure
- Stop immediately
- Report error with details
- Ask: (r)etry, (s)kip, (m)odify, (a)bort
Verification Failure
- Report expected vs actual
- Ask: (i)nvestigate, (p)roceed
Blocker Found
- Document in plan progress
- Report to user
- Wait for guidance
Progress Tracking
Update plan file after each task:
## Progress
### Session [timestamp]
- Task 1.1: COMPLETED
- Task 1.2: COMPLETED - Note: [any notes]
- Task 2.1: IN_PROGRESS
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 121 lines · 54 tokens per session scan A e5123be77110
execute is a skill published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 54 tokens to every session and 629 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
system-boot
Auto-activating session startup - reads memory, orients Claude, announces status. Triggers on session start or when user says "continue", "weiter", "resume".
project-brain
Triggers (all require explicit user request — do NOT activate just because a brain/ folder exists): (1) The user wants to set up project-level memory ("set up project brain", "scaffold project context", "init project brain", "建项目脑"). (2) The user is in a directory containing brain/ AND explicitly asks to resume /…
subagent-strategy
Delegates research and parallel work to sub-agents.
evolution-guide
Explains how Evolving Lite works when the user asks about the system, its features, or how to use it. Triggers on questions like "how does this work", "what is evolving lite", "what hooks are running", "explain the system".
spawn-agent
Spawn worker agents (Gemini CLI or Codex CLI) to keep main context clean. Use for implementation, codebase research, context gathering, or any scoped work that would pollute the orchestrator's context.
flutter-bloc-development
Build Flutter features using BLoC state management, clean architecture layers, and the project's design system. Apply when creating screens, widgets, or data integrations.