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/yaukwan/my-claude-code-workflow/impl-taskgit clone --depth 1 https://github.com/yaukwan/my-claude-code-workflowWhat 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 | $0.00024 | $0.00463 |
| Opus 5 | $0.00012 | $0.00231 |
| Sonnet 5 | $0.00005 | $0.00093 |
| Haiku 4.5 | $0.00002 | $0.00046 |
Grade A, and why
impl-task 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 3d 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.
What it actually says
Phase 1: Check Requirements and Load Task File
- Parse arguments
$ARGUMENTSto extract task file name (required) - If task file name is not provided, exit with error "No task file specified"
- Load
docs/specs/{task_file_name}task file, if it exists. If not, exit with error "Specs file not found"
Phase 2: Parse Task Organization and Execute Per Top-level Task
Parse Available Tasks
Analyze the task file structure to identify all top-level tasks under "## 5. Task Decomposition & Implementation Directives" section:
- Find all "### Task Group X:" entries where X is a number
- Extract task titles, related files, and purposes
- Determine execution order based on task dependencies and file relationships
Execute Each Top-level Task Separately
For EACH top-level task group found (Task Group 1, Task Group 2, etc.):
Use the artisan-impl sub agent to:
- Implement [current task specification requirements] with unified implementation and validation approach
- Automatically update task checkboxes in the specification file
- Provide consolidated implementation and progress report
The artisan-impl agent handles BOTH implementation AND progress tracking in a single atomic operation, ensuring consistency between code state and project tracking.
Phase 3: Final Validation
After all individual task groups are completed:
- Verify overall project completion status in specification file
- Generate final implementation summary if all tasks complete
- Report any tasks that remain incomplete or failed
🔄 Streamlined Workflow
Main Agent → impl-task command
↓
impl-task → artisan-impl sub-agent
↓
artisan-impl → Implements task AND updates progress atomically
↓
Returns unified report with implementation + tracking confirmation
↓
impl-task → Next task group or completion
Usage
# Execute implementation with automatic progress tracking
/impl-task user_management_tasks
# Process another specification file
/impl-task authentication_tasks
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.
- 3d ago First seen · 59 lines · 24 tokens per session scan A 568d62ea86d5
impl-task is a command published in the GitHub repository yaukwan/my-claude-code-workflow (44 stars, last pushed 1y ago), licensed MIT. It adds 24 tokens to every session and 463 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
memory-audit
Audit project memory files for staleness, orphans, bloat, and duplication.
probe
Probe recent changes with 2-3 pointed questions.
lint
Run markdownlint on specified files or the whole project.
ponder
Surface a question worth sitting with.
install-statusline
Install duet statusline to /.claude for a lean, informative status bar.
capture-memory
Capture learnings to MEMORY.md, output compact summary.