Borrowing it
Nothing to install: this file belongs to DavidVujic/my-eca-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/DavidVujic/my-eca-config/main/AGENTS.mdgit clone --depth 1 https://github.com/DavidVujic/my-eca-configWrote 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/davidvujic/my-eca-config/agents-md)<a href="https://agentmods.dev/instructions/davidvujic/my-eca-config/agents-md"><img src="https://agentmods.dev/badge/instructions/davidvujic/my-eca-config/agents-md/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/instructions/davidvujic/my-eca-config/agents-md"><img src="https://agentmods.dev/badge/instructions/davidvujic/my-eca-config/agents-md.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 | $0.03241 | $0.03241 |
| Opus 5.5 | $0.01296 | $0.01296 |
| Sonnet 5.5 | $0.00648 | $0.00648 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade A, and why
my-eca-config AGENTS.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 today.
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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Communication style
The following skill is included automatically via this mention; every agent and subagent follows it in chat and in reports, without loading it: @skills/concise-style/SKILL.md
Review instructions
When the user asks for a code review / PR review / diff review:
- Load the
git-changes-contextskill viaeca__skilland run its commands witheca__gityourself. Subagents have noeca__git. - If the result is
error: "NO_DIFF_FOUND", reply{"status":"no_changes"}and do not spawncode-review. - Otherwise spawn the
code-reviewsubagent configured inagents/code-review.md, passing the rawdiff_contextand the exactdiff_source_command.
After the subagent returns:
- Summarize the findings; if there are none, say "No issues found."
- Spot-check findings that name callers outside the diff with
eca__editor_referencesbefore acting on them. - Address critical and high findings; route fixes to the
implementsubagent. For each finding you do not act on, state why. - End with actions taken and findings left open.
PR review comments instructions
When the user asks to handle review comments on a pull request:
- Fetch them with
eca__git:gh pr view <n> --commentsfor the conversation andgh api repos/{owner}/{repo}/pulls/<n>/commentsfor inline threads (file, line, body, author). - Judge each comment against the code, not the description: read the cited range with
eca__read_file, resolve the symbol witheca__editor_definition, and check blast radius withchiasmus_graph analysis="impact"before agreeing or disagreeing. - Group the outcome per comment: accept (with the planned change), reject (with evidence), or needs clarification.
- Delegate accepted changes to
implementin one batch, then repeat the Review instructions (fetch a fresh diff, then reruncode-review) on the result.
Delegation instructions
- Hand subagents concrete inputs: absolute file paths, the
fileslist for Chiasmus, exact lines from the diff, and the acceptance criteria. Do not make them rediscover what you already know. - Use the built-in
explorersubagent for broad codebase reading that would otherwise flood this context; keep the summary, not the raw files. - Treat subagent output as a claim. After
implement:eca__editor_diagnostics, then theqa-checksubagent when code changed. Aftercode-review: the spot-check described above. Afterqa-check: read the failures yourself before deciding the next step. - Do not redo a subagent's work in the main context; if the result is unusable, respawn with the missing input.
- If
implementreports a user-rejected edit, do not retry automatically. Use the user's existing correction or ask viaeca__ask_user, then resume the same subagent with thechat_idfromspawn_agent. If it cannot be resumed, spawn a newimplementwith a handoff and the current file state.
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.
- today Changed · +4 lines · +229 tokens per session f6a028e4693d
- 21d ago Changed · +3 lines · +28 tokens per session 188e0a127f2c
- 1mo ago Changed · +1 lines · +182 tokens per session b1fa74252f51
- 1mo ago Changed · +16 tokens per session 413c08a0d704
- 1mo ago Changed · +54 lines · +957 tokens per session 4367222b3d07
- 1mo ago Changed · +7 lines · +110 tokens per session 398b31dbf82e
- 1mo ago First seen · 92 lines · 1,719 tokens per session scan A 4db8f2ce9b53
my-eca-config AGENTS.md is an instructions file published in the GitHub repository DavidVujic/my-eca-config (11 stars, last pushed yesterday), licensed MIT. It adds 3,241 tokens to every session, about $0.0130 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.