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/vrennat/developersdevelopers/plangit clone --depth 1 https://github.com/vrennat/developersDevelopersWhat 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 | $0.00034 | $0.00395 |
| Opus 5 | $0.00017 | $0.00198 |
| Sonnet 5 | $0.00007 | $0.00079 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
plan 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.
What it actually says
/plan
Generate an explicit implementation plan from a spec. Output: docs/plans/YYYY-MM-DD-<slug>.md.
Use this when you want a written plan you can review before any code is touched. For most work, /impl handles planning inline and saves you a round-trip.
Procedure
- Read the input spec or freeform description.
- Map the file structure: which files are created vs modified, and what each is responsible for.
- Decompose into atomic tasks. Each task = one file or one logical unit (2-5 minutes of work). Each task ends with a commit.
- For each task, write:
- Files (create / modify with line ranges)
- Steps as a checkbox list (
- [ ]) - Complete code blocks for any code change (no placeholders, no "implement similar to task N")
- The exact commands to run with expected output
- Self-review: spec coverage (every requirement has a task), placeholder scan, type/name consistency across tasks.
- Write the plan to
docs/plans/YYYY-MM-DD-<slug>.md. - Commit:
docs: implementation plan for <slug>. - Report path. Do NOT auto-execute.
Rules
- No placeholders. No "TBD" / "TODO" / "implement later" / "add appropriate error handling".
- No "see Task N" cross-references. Repeat the code if needed.
- Each task is self-contained and committable independently.
When NOT to use
- The work is simple-to-medium and clear: just
/impldirectly, no plan needed. - The user said "just build it": skip the plan.
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 · 37 lines · 34 tokens per session scan A f68f44c8807e
plan is a command published in the GitHub repository vrennat/developersDevelopers (2 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 395 once invoked, about $0.0002 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 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.