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 skills/rickywo/formic/executenpx skills add rickywo/Formic --skill executegit clone --depth 1 https://github.com/rickywo/FormicWhat 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 | $0.00013 | $0.00427 |
| Opus 5 | $0.00006 | $0.00214 |
| Sonnet 5 | $0.00003 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
execute 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
Execute Skill
You are an expert software engineer executing an implementation plan.
Verification status policy
Mark subtasks skipped only for subjective human judgment or access to an unavailable external system. Do not skip writing tests, running tests, type-checking, builds, linting, or local fixture verification merely because setup is needed or a command failed.
Available Tools
Formic maintains a library of reusable tools in .formic/tools/. Each tool is a directory containing:
- A script file (bash, python, or node)
- A
manifest.jsondescribing the tool's name, purpose, command template, and usage count
Using Existing Tools
Before implementing a task from scratch, check .formic/tools/ for tools that may already solve part of the problem:
ls .formic/tools/
cat .formic/tools/<tool-name>/manifest.json
Run a tool using the command in its manifest (replace {{file}} with the target file path). After running a tool successfully, increment its usage count by updating manifest.json.
Creating New Tools
If you discover a reusable operation that could benefit future tasks, create a new tool:
- Create a directory:
.formic/tools/<tool-name>/ - Create the script file (e.g.,
run.shfor bash,run.pyfor Python) - Create
manifest.jsonwith this structure:
{
"name": "<tool-name>",
"description": "What this tool does",
"command": "bash .formic/tools/<tool-name>/run.sh {{file}}",
"created_by": "<current-task-id>",
"usage_count": 0
}
Tool Naming Conventions
- Use kebab-case names (e.g.,
sort-imports,add-license-header) - Name tools after the action they perform, not the task that created them
- Tools should be idempotent where possible
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 · 51 lines · 13 tokens per session scan A 99bd53f01272
execute is a skill published in the GitHub repository rickywo/Formic (41 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 427 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 skills, from other repositories
analyze-performance-traces
Analyze Chrome, Chromium, Electron, React DevTools, or Perfetto-compatible JSON traces and audit user-reported profiling findings without loading large artifacts into context; prove trigger-to-render/layout chains, separate measured facts from source inference, find exact code choke points, classify forced layout and…
tutti-app-release
Set up, review, run, or debug external repositories that publish a Tutti workspace app through the reusable Tutti App Release GitHub Actions workflow. Use for caller workflows, tutti.app.json manifests, @tutti-os/app-release-tools, S3/CloudFront release hosting, latest.json, versions.json, catalog.json, catalog-only…
tutti-test-audit
Audit, design, write, materially revise, or remove Tutti tests. Use whenever Codex changes or reviews unit, component, conformance, integration, regression, platform, or repository tests; enforce a protected product contract, credible failure, correct owning boundary, negative-control evidence, overlap review…
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
assimilate-popular-workflows
This skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md files in repos", "research external skills", "find workflow patterns", "survey the skill landscape", "what skills exist out there", or wants to investigate public repositories for extractable…
catalog-babysitter-users
Discover public GitHub repositories that import defineTask from @a5c-ai/babysitter-sdk and maintain a deduplicated catalog of those repositories in docs/repo-with-babysitter-processes.md. Excludes any repo named "babysitter" (to filter out forks of this monorepo). Invoke when asked to find, discover, catalog, or…