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/tosin2013/helmdeck/claude-mdgit clone --depth 1 https://github.com/tosin2013/helmdeckWrote 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/tosin2013/helmdeck/claude-md)<a href="https://agentmods.dev/instructions/tosin2013/helmdeck/claude-md"><img src="https://agentmods.dev/badge/instructions/tosin2013/helmdeck/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 | $0.00363 | $0.00363 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
helmdeck 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 3d 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
Helmdeck
Read docs/integrations/SKILLS.md for helmdeck-specific instructions when using tools.
Read docs/integrations/pack-demo-playbook.md for example prompts and expected outputs.
When development surfaces something noteworthy, draft a blog post
If your work in this repo turns up something the broader engineering audience would learn from — a quantified cost result, an unexpected interaction between two subsystems, an architectural insight, or a friction story with a clean fix — propose a blog draft alongside the implementation using website/blog/_template.md.
Don't gate on whether it ships. Drafts with draft: true cost nothing to land and zero to discard, but they capture the finding while it's fresh. The blog's value compounds with cadence; treat draft posts as a normal output of development work, not a separate marketing track.
See CONTRIBUTING.md §"Other contribution types" for the workflow.
If the post is research-flavored, also update /research
Helmdeck is, in practice, a research project that ships as software. The pattern is real: hard implementation work — the kind that takes time and money to push through — is what produces the findings worth publishing. Don't lose them.
If the blog post you're drafting is research-flavored (the finding generalizes beyond the immediate fix — a new empirical pattern, an architectural insight, a quantified cost or capability result), add an entry to website/src/pages/research.md in the same change. One-line summary + link to the post / ADR / production change that landed it.
The /research page is the durable, citeable surface that turns "trust me, we're doing research" into "click any entry." It's load-bearing for grant applications and external citations — keep it current.
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.
- 3d ago First seen · 21 lines · 363 tokens per session scan A 224027198cfe
helmdeck CLAUDE.md is an instructions file published in the GitHub repository tosin2013/helmdeck (4 stars, last pushed 10d ago), licensed Apache-2.0. It adds 363 tokens to every session, about $0.0018 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 2026-08-31.
Other instructions, from other repositories
alethia-mcp CLAUDE.md
Claude Code instructions for vitron-ai/alethia-mcp, covering alethia-mcp, build, test, run the bridge locally and demo pages.
blop-mcp AGENTS.md
AGENTS.md instructions for n2400813g/blop-mcp, covering agents.md, project overview, product thesis (internal shorthand), setup & installation and dev: test mcp tools interactively.
blop-mcp CLAUDE.md
Claude Code instructions for n2400813g/blop-mcp, covering claude.md, project overview, product thesis (internal shorthand), setup & installation and dev: test mcp tools interactively.
mcp-server-excel coverage-prevention-strategy.instructions.md
Instructions for sbroenne/mcp-server-excel, covering generated surface coverage, contract change workflow, required checks and common incomplete changes.
mcp-server-excel mcp-llm-guidance.instructions.md
Instructions for sbroenne/mcp-server-excel, a project described as: Automate real Microsoft Excel with AI via MCP Server or CLI — Power Query, DAX, VBA, PivotTables, charts, and 326 operations.
openrouter-mcp-multimodal AGENTS.md
Instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).