Borrowing it
Nothing to install: this file belongs to jackvaughanjr/jamf-platform-mcp-server. 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/jackvaughanjr/jamf-platform-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/jackvaughanjr/jamf-platform-mcp-serverWrote 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/jackvaughanjr/jamf-platform-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/jackvaughanjr/jamf-platform-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jackvaughanjr/jamf-platform-mcp-server/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/jackvaughanjr/jamf-platform-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/jackvaughanjr/jamf-platform-mcp-server/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 | $0.01804 | $0.01804 |
| Opus 5.5 | $0.00722 | $0.00722 |
| Sonnet 5.5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
jamf-platform-mcp-server 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 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working in this repo
Rules for working here. Three companion documents carry what this one deliberately does not:
docs/gateway-reference.md— what the Jamf Platform API Gateway actually does: path shapes, confirmed routes, status semantics, pagination. Findings about a beta product; expect them to change.decisions/— why the project is built this way. Immutable.docs/BACKLOG.md— open work, each entry with why and what done looks like. Start here when resuming. It is public, so tenant-specific open items are kept in Claude Code project memory instead, and the file says so.
Never force-add ignored files
git add -f / git add --force is not permitted in this repo, and neither is
git update-index --add on an ignored path. A .githooks/pre-commit hook rejects
any staged file that .gitignore covers, so a force-add fails at commit time
rather than silently landing.
The ignore list is a data-handling boundary, not tidiness. It guards:
- the OAuth client secret (
.env) — shown exactly once at integration creation - raw gateway responses (
fixtures/raw/,blueprints.json) containing live device serials, usernames, email addresses, IPs, and per-device application inventory
If something currently ignored genuinely belongs in version control, change
.gitignore in its own commit so the decision is reviewable. Rationale:
JPM-0004.
Committed ADRs are immutable
scripts/check-adr-immutability.sh blocks modifying, deleting, or renaming an ADR
that is already committed. Corrections go by a new superseding record. Before a
record has external readers, an in-place edit is available via
ADR_ALLOW_EDIT=1 git commit. In CI, src/adr-guard.ts blocks the same changes
but allows a Status-only superseded-by pointer to an existing record, the one edit
decisions/README.md sanctions. See decisions/README.md.
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 · +22 lines · +345 tokens per session 97de1167e330
- 27d ago Changed · +3 lines · +64 tokens per session b6964bb7a194
- 1mo ago Changed · +11 lines · +216 tokens per session 84d6208710c7
- 2mo ago First seen · 96 lines · 1,179 tokens per session scan A dc9126fe38dd
jamf-platform-mcp-server CLAUDE.md is an instructions file published in the GitHub repository jackvaughanjr/jamf-platform-mcp-server (1 stars, last pushed today), licensed MIT. It adds 1,804 tokens to every session, about $0.0072 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 2026-08-31.
jamf-platform-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| jamf-platform-mcp-server CLAUDE.mdjackvaughanjr/jamf-platform-mcp-server | Instructions file | 1 | today | MIT | A | 1,804 | 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 |