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 skills add alejandro-ventures/llm-agnostic-icm-framework --skill scratchgit clone --depth 1 https://github.com/alejandro-ventures/llm-agnostic-icm-frameworkWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/scratch)<a href="https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/scratch"><img src="https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/scratch/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alejandro-ventures/llm-agnostic-icm-framework/scratch"><img src="https://agentmods.dev/badge/skills/alejandro-ventures/llm-agnostic-icm-framework/scratch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00037 | $0.00646 |
| Opus 5 | $0.00018 | $0.00323 |
| Sonnet 5 | $0.00007 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00065 |
Grade A, and why
scratch 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scratch
Route here ONLY when no specialized workflow in the routing table fits. "General" loosens the task type, never the rules: every CONVENTIONS rule (write-boundary, copy-in-to-edit, dry-run, human gates, no secrets, logging) still applies here in full.
MUST-DO checklist — verify each item BEFORE finishing, none are optional
- Inputs were COPIED into
input/(never read other workflows' folders or references in place). - Every write went through
_core/scripts/sandbox.py(sandbox.guard_write/safe_open_w). - Any third-party import is installed in
.venvAND pinned inrequirements.txt. - One line appended to
output/run-log.csvAND one token-tracker entry logged.
Inputs
| Source | Location | Why |
|---|---|---|
| User data | input/ |
material to work on (copy reference files here first — never edit the original) |
| Reference | (read-only material outside the workspace) | context, pulled minimally |
Process
- Confirm the fallback. If any specialized workflow matches, stop and route there instead.
- Put user-provided files in
input/; write every artifact tooutput/. Nothing leaves the workspace. - Ad-hoc code goes in
scripts/; any write must route through_core/scripts/sandbox.py(sandbox.guard_write(...)). Install packages into.venvand pin them inrequirements.txt. - Gate: any destructive/irreversible step (delete, overwrite, send, move) needs a reviewable plan first and an explicit "yes" in the same turn.
- Append run-log + log to the token-tracker.
- Graduation: if this kind of task recurs, promote it into its own workflow via
shared/templates/rather than lettingscratchbecome a junk drawer.
Outputs
| Artifact | Location | Format |
|---|---|---|
| Result | output/ |
whatever the task needs (readable/plain-text where possible) |
Gates
- Destructive/irreversible actions need an explicit "yes" (see CONVENTIONS).
Run log
timestamp,scratch,<action>,<result> to output/run-log.csv, then
python _core/token-tracker/tracker.py log --workflow scratch --action <action> --source <local|cloud>.
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.
- 8d ago First seen · 44 lines · 37 tokens per session scan A 2572571456d1
scratch is a skill published in the GitHub repository alejandro-ventures/llm-agnostic-icm-framework (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 37 tokens to every session and 646 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 skills, from other repositories
agent-self-scheduling
Schedule AI agent runs with cron, loops, or external clocks while avoiding unsafe tight autonomous timers.
agent-engineering-expert
Build LLM agents that use tools safely: tool design, the agent loop, memory, MCP servers, multi-agent orchestration, sandboxing and prompt-injection defence. Use when the user mentions AI agents, tool use or function calling, MCP or Model Context Protocol, autonomous workflows, multi-agent systems, LangChain or…
junjo-evaluation
Turn a developer's product-quality objective into a complete Junjo Studio-backed evaluation workflow. Use when a coding agent needs to establish a baseline, design or generate typed cases, run or resume application-owned Node, Workflow, or Agent targets, inspect outcomes and exact trace evidence, compare a candidate…
junjo-openai-agents
Add Junjo's optional OpenAI Agents SDK integration to an application. Use when a coding agent needs to install junjo[openai-agents], expose a native Junjo Workflow or Agent as an OpenAI function tool, send standard OpenAI Agent and nested Junjo spans through one application-owned OpenTelemetry provider, declare an…
writing-workspace-jobs
Author FSM workspace jobs. Use when creating, editing, or debugging jobs, signals, or FSM workflows in workspace.yml.
workspace-api
Create, list, update, delete, and clean up workspaces via the daemon HTTP API at $FRIDAYDURL. Use when the user asks to create, edit, delete, or list workspaces, spaces, projects, or environments; add or patch signals / agents / jobs / memory / skills; convert a workspace.yml into a live workspace; wire up triggers…