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/sijeeshmiziha/visionagent/implementgit clone --depth 1 https://github.com/sijeeshmiziha/visionagentWhat 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 | $0.00402 |
| Opus 5 | $0.00000 | $0.00201 |
| Sonnet 5 | $0.00000 | $0.00080 |
| Haiku 4.5 | $0.00000 | $0.00040 |
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 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.
What it actually says
Implement Feature
You are in full autonomous implementation mode. Follow the VisionAgent agentic task approach from CLAUDE.md rigorously.
Task
$ARGUMENTS
Execution Plan
Work through these steps in order without stopping to ask unless genuinely blocked:
1. Understand & Plan
- Read CLAUDE.md for project conventions
- Identify all files that need to be created or modified
- Trace the call chain from public API → implementation
- Check
src/index.tsto understand current exports - Read any existing similar code for patterns to follow
2. Implement
- Write source code in
src/ - Follow naming conventions (kebab-case files, PascalCase interfaces, camelCase functions)
- Use
@/imports internally,visionagentalias in examples - Add explicit return types on all public functions
- No
anyinsrc/— use Zod inference or proper typing
3. Export
- Add exports through the module's
index.ts - Add to
src/index.tsif it's part of the public API
4. Test
- Write tests in
tests/(not co-located) - Use MSW mocks for external API calls
- Run:
npm test - Fix any failures before proceeding
5. Quality Gates
Run these in sequence and fix all issues:
npm run typecheck
npm run lint:fix
npm run format
npm run build
6. Example (if new feature)
- Add an example in
examples/<module>/<feature>.ts - Register it in
examples/lib/registry.ts - Verify it runs:
npm run example -- examples/<module>/<feature>.ts
7. Final Verification
npm run ci
Report what was implemented, what tests were added, and confirm npm run ci passed.
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 · 65 lines · 0 tokens per session scan A 41f608a8ddbb
implement is a command published in the GitHub repository sijeeshmiziha/visionagent (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 402 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.
workflow-classify
Classify task size (S/M/L/XL) and recommend the appropriate workflow pipeline.
verify-loop
자동 재검증 루프 (최대 3회 재시도, 실패 시 자동 수정).
test-tools
Test MCP NixOS Tools (project).
firm
Convene your standing AI staff — memos on every beat, a board session without you, minutes with dissent preserved.
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.