Borrowing it
Nothing to install: this file belongs to ZingerLittleBee/Heeler. 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/ZingerLittleBee/Heeler/main/CLAUDE.mdgit clone --depth 1 https://github.com/ZingerLittleBee/HeelerWrote 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/zingerlittlebee/heeler/claude-md)<a href="https://agentmods.dev/instructions/zingerlittlebee/heeler/claude-md"><img src="https://agentmods.dev/badge/instructions/zingerlittlebee/heeler/claude-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/zingerlittlebee/heeler/claude-md"><img src="https://agentmods.dev/badge/instructions/zingerlittlebee/heeler/claude-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 | $0.01253 | $0.01253 |
| Opus 5.5 | $0.00501 | $0.00501 |
| Sonnet 5.5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
Heeler 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 yesterday.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Heeler
Native iOS companion app for herdr, an agent console over SSH.
Start here
- Implementation or diagnosis: use the source map to find the feature entry, state owner, transport seam, and focused tests.
- Domain terms or architecture: read CONTEXT.md, then the area-specific ADR linked by the source map.
- Tests or builds: use
make helpand the testing guide. For Simulator UI work, read the UI runbook. - App Store or README images: follow
the store screenshot runbook. Agent content
comes from real Agents through
scripts/store-shots.py, not demo data. - Review or regrade: capture the current acceptance amendments, candidate, and evidence in the handoff template.
- RPC, subscriptions, launch/input, or scrolling compatibility: consult versioned herdr observations. Check each observation's version before applying it to a newer server.
Architecture
- SwiftUI, iOS 18+, iPhone and iPad. SSH uses the repository-local
Packages/HeelerSSH(pinned libssh2 and OpenSSL); terminal rendering uses the pinned libghostty-spmGhosttyTerminalproduct (ADRs 0001 and 0004). - On Herdr TUI Hosts, Unix API and Events use NDJSON over direct-streamlocal channels to herdr's socket. Unix Agent and shell terminals use PTY exec (ADR 0011).
- On Herdr TUI Hosts, Native Windows API and Events use
herdr remote-api-bridge; live terminals useherdr terminal session controlover SSH exec (ADR 0018). This is a platform branch, never a fallback after Unix forwarding refusal. - herdr-core Hosts carry one framed link: direct-streamlocal to the core's
socket on Unix, SSH exec of
herdr-core connecton native Windows after a pipe check. Connecting never starts a core on Unix, and on Windows starts one only if it stops in the round trip after that check (ADR 0031). - UI depends on
Transport, not SSH library types. Pane ids are opaque strings. Protocol negotiation enforces a floor, ignores unknown fields, and treats the generated protocol version as advisory. API requests are one-shot; subscribe acknowledgement precedes snapshots, and reconnect requires fresh inventory. - Terminal inventory and retained attachments follow ADR 0017; RSA Key authentication follows ADR 0019. Use the source map's full ADR links.
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.
- yesterday Changed · +6 lines · +92 tokens per session 6afa49b3696a
- 2d ago Changed · -1 tokens per session 06cbbffa2078
- 5d ago Changed · +3 lines · +47 tokens per session 5a1c713f773b
- 12d ago Changed · +6 lines · +115 tokens per session 8fd7cf7126e0
- 23d ago Changed · +1 lines · +18 tokens per session bd538aae7920
- 26d ago Changed · +1 lines · +8 tokens per session be1e53f07821
- 1mo ago Changed · +1 lines · +33 tokens per session 182a7c2f0219
- 1mo ago Changed · +1 lines · +16 tokens per session 5a547d33bddf
- 1mo ago Changed · -2 lines · -3,408 tokens per session 15947dae54c8
- 1mo ago First seen · 70 lines · 4,333 tokens per session scan A ccd56a97a49a
Heeler CLAUDE.md is an instructions file published in the GitHub repository ZingerLittleBee/Heeler (776 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,253 tokens to every session, about $0.0050 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.
Heeler CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Heeler CLAUDE.mdZingerLittleBee/Heeler | Instructions file | 776 | yesterday | Apache-2.0 | A | 1,253 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |