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/aaronnat23/disp8ch/coding-agentnpx skills add aaronnat23/disp8ch --skill coding-agentgit clone --depth 1 https://github.com/aaronnat23/disp8chWhat 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 | $0.00198 |
| Opus 5 | $0.00000 | $0.00099 |
| Sonnet 5 | $0.00000 | $0.00040 |
| Haiku 4.5 | $0.00000 | $0.00020 |
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
Autonomous code generation, iterative self-healing, and engineering best practices.
- Write code in small, testable units. State assumptions explicitly before generating.
- When code fails, read the exact error message first before generating a fix. Never guess at errors.
- Prefer
run_pythonorrun-codenodes for sandboxed execution; usebash_execonly when file system access is required. - Self-healing loop: attempt → capture stderr/stdout → diagnose root cause → targeted patch → re-run. Stop after the configured max iterations and report what failed.
- Always write a brief plan comment at the top of generated code blocks.
- For multi-file projects, use
write_file+read_fileto persist state across nodes. - Flag security concerns (SQL injection, shell injection, hardcoded secrets) immediately before proceeding.
- When generating TypeScript, use strict mode types and named exports. When generating Python, use type hints.
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 · 13 lines · 0 tokens per session scan A 27d24989328f
coding-agent is a skill published in the GitHub repository aaronnat23/disp8ch (98 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 198 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 2026-08-30.
Other skills, from other repositories
graphify
Converts this codebase into a queryable knowledge graph so AI sessions query graph.json (71.5x fewer tokens) instead of reading raw source files. Integrates with Claude Code and Codex via repo hooks that auto-refresh on session start and after turns.
repowise-intelligence
Implements codebase intelligence layers similar to repowise-dev/repowise. Provides dependency graph, git history, auto-generated documentation, and architectural decisions intelligence for AI agents.
agent-harness
Build and run a structured agent harness — an outer loop that gives an LLM a defined set of tools (capabilities) and drives it to task completion. Based on the architecture from the OpenAI Agents SDK blog post: an Agent is a for-loop with an LLM running tools until done.
pro-workflow
Core AI coding workflow. Orchestrates 8 patterns: Scout → Plan → Implement → Review, with smart commits, session rituals, and continuous learning capture. This is the master skill — invoke it at the start of any non-trivial task.
parallel-agents
Decompose a large task into N independent subtasks and dispatch them as parallel subagents, then aggregate results. Inspired by the Modal + OpenAI Agents SDK pattern of spawning multiple coding agents simultaneously — each working in its own sandbox — to discover solutions faster through parallelism.
resource-panel
Track, display, and summarise all resources consumed or produced during an agent session: files read/written, URLs fetched, tools called, tokens used, and external dependencies touched.