Borrowing it
Nothing to install: this file belongs to cboone/agent-harness-plugins. 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/cboone/agent-harness-plugins/main/.github/instructions/tmpfile.instructions.mdgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/tmpfile)<a href="https://agentmods.dev/instructions/cboone/agent-harness-plugins/tmpfile"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/tmpfile/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/cboone/agent-harness-plugins/tmpfile"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/tmpfile.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 | $0.00820 | $0.00820 |
| Opus 5.5 | $0.00328 | $0.00328 |
| Sonnet 5.5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
agent-harness-plugins tmpfile.instructions.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 25d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tmpfile pattern review instructions
Temporary paths in this repository target ${TMPDIR:-/tmp} rather than a literal /tmp, because the macOS Bash sandbox denies /private/tmp and the per-user directory mktemp picks by default. plugins/use-git/skills/use-git/references/tmpfile-pattern.md is the canonical description. These specific shapes are correct and have been checked, so they are not defects:
mktemp -u "${TMPDIR:-/tmp}/<prefix>-XXXXXX"is the intended form, for files, as ismktemp -d "${TMPDIR:-/tmp}/<prefix>-XXXXXX"for directories. A file already written this way needs no further change; do not report it as an unresolved gap. Within this pattern, a baremktemp, a baremktemp -d, amktemp -ut <prefix>, or a literal/tmp/...template is a finding, because each of those selects a directory the sandbox denies.- Plain
mktempstays correct for security-sensitive temporary files, and is not a finding. The canonical reference deliberately keeps it for content written through a shell redirect rather than the Write tool, because-udoes not atomically reserve the name and both man pages call it unsafe. The general shell style references inwrite-bash-scriptsandwrite-zsh-scriptsrecommend plainmktempfor exactly that reason, and a table contrastingtmp=$(mktemp)with a predictable/tmp/...path is showing the safe form beside the unsafe one. Leave all of those alone. The rule above governs the non-secret pattern only: a body passed to a command's file flag, or a scrut test's working directory. - The
:-/tmpfallback is deliberate. A bare${TMPDIR}resolves to an empty string on a shell that leaves it unset and writes at the filesystem root. macOS usually sets$TMPDIRwith a trailing slash, so the expansion can produce a doubled slash mid-path, which every POSIX filesystem treats as one separator. -uis required for the file form, even though both man pages call it unsafe in general. Plainmktempcreates the file, and the Write tool refuses to overwrite a file it has not read first. The trade-off is scoped to non-secret bodies such as pull request, issue and release text.- An example path such as
/tmp/claude-501/gh-pr-body-x4y5z6is illustrative output, showing whatmktempprints under the sandbox. It is not a hardcoded path and is not a finding.
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.
- 25d ago First seen · 23 lines · 820 tokens per session scan A dea46230f387
agent-harness-plugins tmpfile.instructions.md is an instructions file published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 820 tokens to every session, about $0.0033 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 2026-09-21.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).