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 instructions/oldskultxo/aictx/copilot-instructionsgit clone --depth 1 https://github.com/oldskultxo/aictxWrote 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/instructions/oldskultxo/aictx/copilot-instructions)<a href="https://agentmods.dev/instructions/oldskultxo/aictx/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/oldskultxo/aictx/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.00445 | $0.00445 |
| Opus 5 | $0.00222 | $0.00222 |
| Sonnet 5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
aictx copilot-instructions.md 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 5d 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
AICTX GitHub Copilot integration
These are repository custom instructions for GitHub Copilot. AICTX cannot force Copilot to run commands, but Copilot should follow this lifecycle whenever command execution is available.
Critical lifecycle:
- Prefer AICTX MCP tools when available; fall back to AICTX CLI commands otherwise.
- MCP-first startup: if AICTX MCP tools are already visible, use those tools for resume/finalize. If they are not visible but
.mcp.jsonor.vscode/mcp.jsonexists, first use the runner tool-discovery mechanism when available (for example search foraictx resume finalize lifecycle) so lazy-loaded MCP namespaces can attach, then have the runner attach/start the configured stdio MCP server before the first AICTX command of each new session. If MCP tools still are not attached after discovery/attachment, state that MCP config exists but tools are unavailable in this runner and use the CLI fallback. - For non-trivial repository tasks, first run exactly once:
aictx resume --repo . --task "<task goal>" --agent-id copilot --adapter-id copilot-vscode --json. - Use the returned resume capsule as the operational brief before broad repo scanning.
- Before the final response, run exactly once:
aictx finalize --repo . --status success|failure --summary "<what happened>" --agent-id copilot --adapter-id copilot-vscode --json. - Append the AICTX final summary from finalize when available. Render every provided summary section, including
details,continuity_view_file, andcontinuity_view_online; preserve Continuity View file links and Mermaid online view links; do not replace URLs with placeholders and do not manually reconstruct or retype pako URLs. If command execution is unavailable, say that the AICTX lifecycle could not be executed. - Do not inspect
.aictx/directly during normal startup; useaictx resume. - Do not run exploratory AICTX commands during normal startup.
Verification tip: in Copilot Chat, expand response References and confirm .github/copilot-instructions.md is listed.
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.
- 5d ago First seen · 18 lines · 445 tokens per session scan A 81450889d549
aictx copilot-instructions.md is an instructions file published in the GitHub repository oldskultxo/aictx (57 stars, last pushed 2mo ago), licensed MIT. It adds 445 tokens to every session, about $0.0022 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 instructions, from other repositories
agent-memory-kit CLAUDE.md
Claude Code instructions for awrshift/agent-memory-kit, covering working on memory kit, rules that are easy to get wrong, before committing a change to hooks or skills, docs that must stay true in the same commit and language.
thoughtdag AGENTS.md
AGENTS.md instructions for chenxiachan/thoughtdag, covering agents.md, 常用命令, 架构 and 约定.
githits-cli AGENTS.md
AGENTS.md instructions for githits-com/githits-cli, covering githits agent instructions, general, architecture, tool output ux and testing.
ryzome-mcp-plugins CLAUDE.md
Instructions for 0xPlaygrounds/ryzome-mcp-plugins, covering agents.md, what this is, commands, per-package and architecture.
lossless-agent-skills CLAUDE.md
Instructions for lossless-group/lossless-agent-skills, covering agent instructions for lossless-agent-skills, symlink sync — opening & closing habit, public skills, private config, vendored upstream submodules — do not overlay them and browser-drive verification (playwright mcp + claude chrome).
pluribus copilot-instructions.md
Instructions for caioribeiroclw-pixel/pluribus, covering project, stack, conventions, constraints and goals.