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 commands/eveld/claude/implementgit clone --depth 1 https://github.com/eveld/claudeWhat 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 | $0.00000 | $0.01155 |
| Opus 5 | $0.00000 | $0.00577 |
| Sonnet 5 | $0.00000 | $0.00231 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
implement 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement Plan
You are implementing an approved plan systematically.
Initial Response
Check if parameters were provided:
- If plan file provided: Detect format and read FULLY
- Personal format:
thoughts/{namespace}/NNNN-description/plan.md - Shared format:
thoughts/shared/NNNN-description/plan.md - Old format:
thoughts/shared/plans/YYYY-MM-DD-NN-*.md
- Personal format:
- If no parameters: Show usage message and wait
Usage message:
I'll help you implement an approved plan. Please provide the path to the plan file.
Example (personal): `/implement thoughts/erik/0005-authentication/plan.md`
Example (shared): `/implement thoughts/shared/0042-authentication/plan.md`
Example (old format): `/implement thoughts/shared/plans/2026-02-03-01-auth.md`
Workflow
Step 1: Read Plan
- Read plan file FULLY (no limit/offset)
- Detect format (feature directory or legacy)
- Check for existing checkboxes (may be partially complete)
- Understand all phases and success criteria
Step 2: Read Context Documents
-
Read changelog if it exists in same directory as plan:
changelog.md- Works for both personal and shared paths
- Understand what's been completed so far
- Note deviations from previous phases
- Adapt current phase based on actual state (auto-correction)
- If changelog doesn't exist, this is the first phase
-
Check if plan references
thoughts/notes/commands.md- If yes and exists: Read it
- If yes but doesn't exist: Use
discover-project-commandsskill, then read
-
Check if plan references
thoughts/notes/testing.md- If yes and exists: Read it
- If yes but doesn't exist: Use
discover-test-patternsskill, then read
Step 3: Analyze with Agents (NEW)
DO NOT read files directly in main context
Before implementing, spawn analysis agents in parallel:
Task(subagent_type="workflows:codebase-analyzer",
prompt="Analyze [component] architecture for this phase.
Return 2-3k summary with key patterns and integration points.")
Task(subagent_type="workflows:codebase-pattern-finder",
prompt="Find similar implementations of [feature].
Return 3k of concrete examples.")
Task(subagent_type="workflows:thoughts-analyzer",
prompt="Extract insights from changelog.md about previous phases.
Return 2k of deviations and learnings relevant to this phase.")
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.
- yesterday First seen · 153 lines · 0 tokens per session scan A b55740258110
implement is a command published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,155 tokens. 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 commands, from other repositories
design-review
Workflow recipe — review a design end-to-end, ending in measured numbers rather than adjectives, by chaining 4 skills.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
validate-dependencies
Validate all task dependencies for issues.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
config
Command "config" from sdebruyn/fabric-dw-mcp-cli, covering configuration & defaults, http retry budget, sql retry budget, mcp workspace allowlist {#mcp-workspace-allowlist} and mcp server log level.