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/jnarowski/agentcmd/implement-specgit clone --depth 1 https://github.com/jnarowski/agentcmdWhat 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 | $0.00011 | $0.02816 |
| Opus 5 | $0.00005 | $0.01408 |
| Sonnet 5 | $0.00002 | $0.00563 |
| Haiku 4.5 | $0.00001 | $0.00282 |
Grade A, and why
implement-spec 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 today.
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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement
Follow the Workflow steps in the exact order to implement the spec then Report the completed work.
Variables
- $specIdOrNameOrPath: $1 (required) - Either a timestamp ID (e.g.,
2510241201), feature name (e.g.,workflow-safety), or full path
Instructions
Parse and resolve $specIdOrNameOrPath:
- If it's a full path (contains
/): use as-is - Otherwise, look up in
.agent/specs/index.json:- For timestamp ID: Match by
idfield - For feature name: Fuzzy match path (e.g.,
message-queuematchestodo/2510241201-message-queue-implementation/spec.md) - Use path from index:
.agent/specs/{path}
- For timestamp ID: Match by
- If not found in index.json, fallback to directory search:
- Search in order: todo/, backlog
- For ID: Pattern
{id}-*/spec.md - For feature name: Pattern
*{feature-name}*/spec.md(fuzzy match)
- If still not found: stop and report error
Task Tracking Requirements
CRITICAL: You MUST track your progress in the spec file as you work. This is NOT optional.
What to Update
-
Individual Tasks - Check off IMMEDIATELY after completing each task:
- Change
- [ ] 1.1 Task descriptionto- [x] 1.1 Task description - Do this AFTER finishing each task, NOT in batches
- Never move to the next task without checking off the current one
- Change
-
Completion Notes - Fill in after finishing each task group/phase:
- Each task group has a
#### Completion Notessection - Write 2-4 bullet points with:
- What was implemented
- Any deviations from the plan
- Important context for reviewers
- Known issues or follow-ups
- Each task group has a
Example of Good Progress Tracking
Before starting task 1.1:
### 1: Project Initialization
- [ ] 1.1 Initialize Bun project
- [ ] 1.2 Configure package.json
After completing task 1.1:
### 1: Project Initialization
- [x] 1.1 Initialize Bun project
- [ ] 1.2 Configure package.json
After completing all tasks in group 1:
### 1: Project Initialization
- [x] 1.1 Initialize Bun project
- [x] 1.2 Configure package.json
#### Completion Notes
- Project initialized with Bun and TypeScript
- Used stricter tsconfig settings than spec suggested for better type safety
- All dependencies installed successfully
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.
- today First seen · 334 lines · 11 tokens per session scan A 3fbec5392adb
implement-spec is a command published in the GitHub repository jnarowski/agentcmd (18 stars, last pushed 8mo ago), licensed MIT. It adds 11 tokens to every session and 2,816 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 2026-09-01.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.