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/bjornjee/agent-dashboard/claude-mdgit clone --depth 1 https://github.com/bjornjee/agent-dashboardWrote 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/bjornjee/agent-dashboard/claude-md)<a href="https://agentmods.dev/instructions/bjornjee/agent-dashboard/claude-md"><img src="https://agentmods.dev/badge/instructions/bjornjee/agent-dashboard/claude-md.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 | $0.00879 | $0.00879 |
| Opus 5 | $0.00439 | $0.00439 |
| Sonnet 5 | $0.00176 | $0.00176 |
| Haiku 4.5 | $0.00088 | $0.00088 |
Grade A, and why
agent-dashboard CLAUDE.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-dashboard
Go conventions
External commands must go through interfaces
Never call exec.Command or exec.CommandContext directly in business logic. All external command execution must go through a mockable interface with a package-level variable that tests can swap.
Pattern:
// 1. Define the interface in a runner.go file
type Runner interface {
Output(ctx context.Context, name string, args ...string) ([]byte, error)
}
// 2. Production implementation
type execRunner struct{}
func (r *execRunner) Output(ctx context.Context, name string, args ...string) ([]byte, error) {
return exec.CommandContext(ctx, name, args...).Output()
}
// 3. Package-level variable
var runner Runner = &execRunner{}
The only files allowed to import "os/exec" are runner/interface implementation files (e.g. runner.go, tmux.go). If you need a new command execution pattern, extend the existing interface rather than calling exec.Command directly.
Tests must use mocks, never real subprocesses
Tests must never spawn real subprocesses (git, gh, tmux, open, etc.). Always use mockery-generated mocks from internal/mocks/. Swap the package-level runner in tests:
m := mocks.NewMockGitRunner(t)
orig := gitRunner
gitRunner = m
t.Cleanup(func() { gitRunner = orig })
Mocks are generated by mockery — config is in .mockery.yaml. After changing an interface, regenerate with mockery.
Testing
- Run tests with
CGO_ENABLED=0 go test -race ./...(CGO disabled to avoid AMFI kills on macOS) - The
-raceflag is mandatory — it catches data races that cause tmux server crashes
Per-harness packages
The dashboard supports two coding-agent harnesses today: claude and codex. Per-harness logic lives in internal/harness/<name>/ for spawn-command construction and internal/<harness>/ for reading the harness-specific state files. Adding another harness means:
- Implement
domain.Harnessunderinternal/harness/<name>/with*runner.gofor anyos/execcalls (same conventions as above). - Register the name in
internal/harness/registry.goResolve(). - Add a
<Name>HarnessSettingsstruct tointernal/domain/types.goand wire it intoHarnessSettings. - Route per-harness flags in
internal/harness/spawnopts.goso unused fields stay zero-valued. - If the harness has its own conversation/state schema, add a reader under
internal/<harness>/and route throughinternal/conversation/router.goRead()(dispatches onagent.Harness). - Update hook scripts (
adapters/claude-code/scripts/hooks/agent-state-fast.jsdetectHarness) so the SessionStart hook stamps the harness name in the per-agent state file — without that, the router can't dispatch.
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.
- 4d ago First seen · 64 lines · 879 tokens per session scan A d2b135594359
agent-dashboard CLAUDE.md is an instructions file published in the GitHub repository bjornjee/agent-dashboard (21 stars, last pushed 1mo ago), licensed MIT. It adds 879 tokens to every session, about $0.0044 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
praktor CLAUDE.md
Claude Code instructions for mtzanidakis/praktor, covering praktor, quick context, architecture, project structure and key commands.
hrdx AGENTS.md
AGENTS.md instructions for patriceckhart/hrdx, covering working agreement for hrdx, product intent, starting a task, code ownership map and correctness contracts.
kungfu copilot-instructions.md
Copilot instructions for kungfu-systems/kungfu: Read and follow AGENTS.md before proposing or running changes. It is the shared agent router for this repository, including the canonical Shifu development and build entrypoint.
agents CLAUDE.md
Instructions for eloylp/agents, covering claude.md, project overview, directory structure, config model and build & run.
ken CLAUDE.md
Claude Code instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.