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/memgrafter/flatmachines/custom_coding_workflownpx skills add memgrafter/flatmachines --skill custom_coding_workflowgit clone --depth 1 https://github.com/memgrafter/flatmachinesWhat 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 | $0.00025 | $0.00171 |
| Opus 5 | $0.00013 | $0.00086 |
| Sonnet 5 | $0.00005 | $0.00034 |
| Haiku 4.5 | $0.00003 | $0.00017 |
Grade A, and why
coding-agent 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
Coding Agent
An agentic coding assistant with human-in-the-loop review.
Usage
cd python && ./run.sh "Add input validation to the User model" --cwd /path/to/project
Flow
- Explore — Gathers codebase context
- Plan — Generates implementation plan → human reviews
- Execute — Applies changes using MCP filesystem
- Verify — Reviews changes → human approves
Skills Integration
Symlink skills for the agent to use:
ln -s /path/to/skills .skills
The agent loads skills on-demand from .skills/ directory.
What ships with it
39 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .gitignore 97 B
- AGENTS.md 11 B
- CLAUDE.md 11 B
- CODING_AGENT_DIFF_MATCHING_BRAINSTORM.md 3.1 KB
- CODING_AGENT_IMPROVEMENT_IDEAS.md 5.0 KB
- config/agents/coder.yml 2.2 KB
- config/agents/planner.yml 2.1 KB
- config/agents/reviewer.yml 1.3 KB
- config/machine.yml 3.9 KB
- config/tools.yml 1.1 KB
- js/hello_world.py 22 B runs code
- js/package-lock.json 18 KB
- js/package.json 614 B
- js/README.md 1.8 KB
- js/run.sh 2.0 KB runs code
- js/src/coding_agent/hooks.ts 20 KB runs code
- js/src/coding_agent/main.ts 3.1 KB runs code
- js/tsconfig.json 406 B
- MACHINES.md 1.1 KB
- PIMONO_SUBAGENTS_EXTENSION_DISCORDMSG.md 1.1 KB
- python/pyproject.toml 467 B
- python/run.sh 2.3 KB runs code
- python/src/coding_agent/__init__.py 35 B runs code
- python/src/coding_agent/hooks.py 28 KB runs code
- python/src/coding_agent/main.py 3.5 KB runs code
- python/test.sh 1.0 KB runs code
- python/tests/__init__.py 174 B runs code
- python/tests/integration/__init__.py 99 B runs code
- python/tests/integration/test_codebase.py 7.6 KB runs code
- python/tests/integration/test_review.py 6.3 KB runs code
- python/tests/integration/test_security.py 7.2 KB runs code
- python/tests/integration/test_workflow.py 8.1 KB runs code
- python/tests/unit/__init__.py 100 B runs code
- python/tests/unit/test_apply.py 9.7 KB runs code
- python/tests/unit/test_display.py 4.8 KB runs code
- python/tests/unit/test_hooks_noninteractive_and_read.py 2.2 KB runs code
- python/tests/unit/test_parser.py 8.3 KB runs code
- README.md 1.4 KB
- WALKTHROUGH.md 2.1 KB
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 · 31 lines · 25 tokens per session scan A 8b0b0aaa26a7
coding-agent is a skill published in the GitHub repository memgrafter/flatmachines (37 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 171 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
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV…
thinking-out-loud
A contract for what the agent does when a long, messy, stream-of-consciousness ramble arrives (usually voice dictation): act on nothing until the echo brief is approved. The echo audits the entire transfer, mission, locked decisions and constraints, open questions, flips and parked tangents, with the model's…
hugging-face-datasets
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, streaming row updates, and SQL-based dataset querying/transformation. Designed to work alongside HF MCP server for comprehensive dataset workflows.
hugging-face-paper-publisher
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.