DashClaw AGENTS.md

Repository guidance for DashClaw, including design rules, a note about disabled tooling, and instructions for using GitNexus to understand the code. GitNexus is a code-intelligence tool that maps symbols, relationships, and execution flows.

In plain words
What is it for?
Use it before changing DashClaw's interface, copy, or visual design, and when tracing code dependencies or execution paths. It also records the command for refreshing the GitNexus index when its data is outdated.
Why use it?
It helps agents follow the project's visual standards and assess how a code change may affect related parts of the application. It also states which unstable tool should not block normal development.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/ucsandman/dashclaw/agents-md
Clone the repo
git clone --depth 1 https://github.com/ucsandman/DashClaw

Made for: Codex, OpenCode.

Per session 2,860 This file is loaded in full into every session.
When invoked 2,860 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02860 $0.02860
Opus 5 $0.01430 $0.01430
Sonnet 5 $0.00572 $0.00572
Haiku 4.5 $0.00286 $0.00286

Measured 2d ago against content hash f509831b3a7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

DashClaw 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 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.

AGENTS.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tooling Note

The previous desloppify integration and mandatory pre-push rule have been disabled.

Reason:

  • the external tool is currently unstable in this environment,
  • it should not block normal development or commits until it is repaired and reintroduced intentionally.

Design Context

Before any UI, design, copy, or marketing/visual change, read .impeccable.md at the repo root first. It is the canonical design context: users, brand personality, aesthetic direction, 4 anti-references, and the 7 tiebreaker principles (evidence over decoration; brand orange as signal not noise; calm under pressure; token-first; developer-reader first; WCAG 2.1 AA floor; four anti-references guardrail). Never hardcode hex values — use the CSS tokens in app/globals.css and the Tailwind theme extension.

GitNexus — Code Intelligence

This project is indexed by GitNexus as DashClaw (18462 symbols, 34472 relationships, 300 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.

Index stale? Run node .gitnexus/run.cjs analyze from the project root — it auto-selects an available runner. No .gitnexus/run.cjs yet? npx gitnexus analyze (npm 11 crash → npm i -g gitnexus; #1939).

Always Do

  • MUST run impact analysis before editing any symbol. Before modifying a function, class, or method, run impact({target: "symbolName", direction: "upstream"}) and report the blast radius (direct callers, affected processes, risk level) to the user.
  • MUST run detect_changes() before committing to verify your changes only affect expected symbols and execution flows. For regression review, compare against the default branch: detect_changes({scope: "compare", base_ref: "main"}).
  • MUST warn the user if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.
  • When exploring unfamiliar code, use query({search_query: "concept"}) to find execution flows instead of grepping. It returns process-grouped results ranked by relevance.
  • When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use context({name: "symbolName"}).
  • For security review, explain({target: "fileOrSymbol"}) lists taint findings (source→sink flows; needs analyze --pdg).

Read the full file on GitHub · 183 lines

Changes

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.

  1. 2d ago First seen · 183 lines · 2,860 tokens per session scan A f509831b3a7a

Subscribe to this mod's changes

DashClaw AGENTS.md is an instructions file published in the GitHub repository ucsandman/DashClaw (296 stars, last pushed 4d ago), licensed MIT. It adds 2,860 tokens to every session, about $0.0143 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.