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/nicepkg/vsync/create-taskgit clone --depth 1 https://github.com/nicepkg/vsyncWhat 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 | $0.00008 | $0.03357 |
| Opus 5 | $0.00004 | $0.01679 |
| Sonnet 5 | $0.00002 | $0.00671 |
| Haiku 4.5 | $0.00001 | $0.00336 |
Grade B, and why
create-task scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- [ ] Can read Codex config from `~/.codex/config.toml` How it starts
The opening of the file, as written. The whole thing — 500 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Task - vsync
Create a new task in TASKS.md for a feature, bugfix, or refactoring work.
Current Context
- Current branch: !
git branch --show-current - Git status: !
git status --short | head -20
Current Task Status
!tail -30 TASKS.md | grep -E "^##|^\*\*|^-"
Instructions
1. Task Type Detection
Parse $ARGUMENTS to determine task type:
- feature: New functionality (e.g., "Add Codex adapter", "Support user-level config")
- bugfix: Fix existing issue (e.g., "Fix env var expansion in OpenCode adapter")
- refactor: Code improvement (e.g., "Extract common adapter logic")
2. Before Creating Task - CRITICAL READS
Read these to understand context:
| Document | Purpose | What to Check |
|---|---|---|
| docs/prd.md | Specification | Is this in MVP scope? (Section 8) |
| CLAUDE.md | Implementation rules | Does it conflict with core rules? |
| TASKS.md | Existing tasks | Is there already a task for this? |
| docs/config.md | Project config | Does it affect config values? |
3. Scope Validation
MVP Scope (INCLUDED):
- ✅ Skills sync (Claude Code → Cursor, OpenCode)
- ✅ MCP sync (Claude Code → Cursor, OpenCode)
- ✅ Safe mode / Prune mode
- ✅ Project-level config
- ✅ CLI commands (init, sync, plan, status, list, clean)
- ✅ MCP security
- ✅ Atomic writes
- ✅ Env var preservation
v1.1 Scope (EXCLUDED from MVP):
- ❌ Agents sync
- ❌ Commands sync
- ❌ Codex adapter
- ❌ User-level config
- ❌
importcommand - ❌ Watch mode
If task is v1.1 scope: Ask user if they want to update PRD first or defer to v1.1.
4. Impact Analysis
Analyze which modules this task will affect:
Adapters (cli/src/adapters/):
- New adapter: Create new file + register in registry
- Adapter modification: Update existing adapter + tests
- Affects: PRD Section 2 (config formats)
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 · 500 lines · 8 tokens per session scan B a20b087465f9
create-task is a command published in the GitHub repository nicepkg/vsync (57 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 3,357 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
init-project
Configure the baseline for this specific project. Invokes the scout skill, then claude-automation-recommender, populates .claude/project.json, pre-creates lazy directories, re-renders swarm-worker.md from its template with any stack-specific skills appended, appends a §16 addendum to docs/init/seed.md, runs…
sql_schema
Command "sql_schema" from agentis-tools/ctx, covering ctx sql — public schema (v1), stability contract, views, v1.symbols — one row per symbol and v1.edges — one row per relationship.
coograph-review
Review the changes in scope for spec compliance, convention violations, logic bugs, and architectural issues. You review — you do not author. Never edit files.
coograph-verify
Verify that the described work is complete and correct. Provide evidence for every claim. You verify — you do not implement or fix style.
hotspots
Rank files and symbols by churn x complexity to find refactoring hotspots.
approve-direction
Record human approval of a workflow's direction (the intake + its acceptance criteria + the CO-A evidence). The Direction Approval Guard hook blocks Claude from ever writing approval tokens; this command is the only sanctioned path. Must be user-invoked. Replaces the retired /approve-spec gate (D3/CO-E gate-collapse)…