agent-harness-plugins: Instructions file for GitHub Copilot

.github/instructions/shell.instructions.md

agent-harness-plugins shell.instructions.md is an instructions file for GitHub Copilot from cboone/agent-harness-plugins. It costs 1,669 tokens per session, scanned A, original, MIT.

A set of project-specific rules for reviewing shell scripts, which are text files that automate commands in a terminal.

In plain words
What is it for?
It is for checking shell-script changes against the project's established conventions.
Why use it?
It gives reviewers agreed rules for portability and safe handling of files, paths, and processes on macOS and Linux.

Instructions file for GitHub Copilot

Written for GitHub Copilot: a Copilot instructions file. Also seen: mentions AGENTS.md.

This is cboone/agent-harness-plugins's own configuration. It tells GitHub Copilot how to work on agent-harness-plugins itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agent-harness-plugins configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/cboone/agent-harness-plugins/main/.github/instructions/shell.instructions.md
Clone the repo
git clone --depth 1 https://github.com/cboone/agent-harness-plugins

Made for: GitHub Copilot.

Wrote 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.

agentmods badge for agent-harness-plugins shell.instructions.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/shell/github.svg)](https://agentmods.dev/instructions/cboone/agent-harness-plugins/shell)
Your own site
<a href="https://agentmods.dev/instructions/cboone/agent-harness-plugins/shell"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/shell/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.

agentmods 80×15 button for agent-harness-plugins shell.instructions.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/cboone/agent-harness-plugins/shell"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/shell.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,669 This file is loaded in full into every session.
When invoked 1,669 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01669 $0.01669
Opus 5.5 $0.00668 $0.00668
Sonnet 5.5 $0.00334 $0.00334
Haiku 4.5 $0.00167 $0.00167

Measured 3d ago against content hash 22c0ba3daf89, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-harness-plugins shell.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 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.

.github/instructions/shell.instructions.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Shell script review instructions

Bundled scripts here run on macOS and Linux alike, so portability findings are welcome. These specific ones are not defects, and have been checked:

  • git worktree list --porcelain -z is the only form that is parsed. The newline-delimited form splits a worktree path containing a newline across two apparent fields. NUL is the one byte a path cannot hold, so -z plus read -r -d '' is correct for every path a filesystem allows. A read -d '' loop also needs || [[ -n "${line}" ]] so a final field carrying no terminator is not discarded.

  • flock is deliberately absent. macOS has no flock(1), which is why mutual exclusion here uses mkdir, which is atomic on every filesystem these scripts run on.

  • kill -0 <pid> is a liveness test, not a terminate. It is the POSIX interface and keeps its name under the neutral-terminology convention, which exempts names the world already fixed.

  • A "$(< path)" read is always preceded by -f and -r tests. That expansion fails during expansion rather than as a command, so a redirection on the assignment and a trailing || both miss it and Bash exits with its own unprefixed diagnostic. -r alone is insufficient: it is true for a readable directory. A scrut case in tests/scrut/repo-tooling.md enforces this.

  • local is declared separately from command substitution (local x then x="$(cmd)") on purpose: local always returns 0 and would mask the command's exit code.

  • # shellcheck disable=SC2016 at file scope is intentional in scripts built around jq filters. The $name tokens inside single-quoted jq programs are jq variables bound with --arg, not shell expansions.

  • jq's sub and gsub take an optional third flags argument. sub/3 and gsub/3 are builtins alongside sub/2 and gsub/2, so sub("^copilot"; ""; "i") is a case-insensitive substitution, not a call with a surplus operand. Confirm with jq -n 'builtins | map(select(startswith("sub/") or startswith("gsub/")))', which lists all four. The same applies to scan/2, match/2, test/2, capture/2 and splits/2.

  • jq -n with inputs reads every input record, the first included. -n binds . to null instead of the first record; it does not stop jq reading standard input, and inputs consumes all of it. printf 'a\nb\n' | jq -Rnc '[inputs]' prints ["a","b"]. This is the idiom for a single pass that stops early with label/break, as in notify's TURN_JQ.

  • gh api --paginate without --jq concatenates REST array pages into one array. A paginated array endpoint yields a single JSON document, so a downstream type == "array" check holds at any page count and no flattening step is needed. --jq is what changes this: gh applies the filter to each page separately, so --paginate --jq 'length' over three pages emits three numbers. --slurp is for the array-of-arrays shape and is required only when page boundaries must be preserved, as in a probe that pipes into a standalone jq and takes last across all pages. The gh api --help line "Each page is a separate JSON array or object" describes the GraphQL and object-returning cases; do not read it as applying to REST array endpoints.

  • fetch_thread_index in resolve-copilot-threads caps each thread at comments(first: 100) on purpose. The index is a lookup table, not the audit's source of comments: audit reads every review comment through the paginated REST endpoint and looks each one up in it. A comment beyond the first 100 in a thread is missing from the index and is reported as in no thread, so the cap can mislabel a reason but cannot make the audit report a clean surface. Do not ask for the nested connection to be paginated.

  • notify's run_alerter stops each alerter with SIGKILL after WAIT_LIMIT seconds on purpose. SIGTERM and SIGINT make alerter remove the delivered banner; SIGKILL leaves it in Notification Center. Each run_alerter stops only its own child alerter, within 60 seconds at most, so it needs no PID start-time check, lock or shared state. Do not ask for a gentler signal, a lock or a start-time check.

Read the full file on GitHub · 39 lines

Changes

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.

  1. 3d ago Changed · +2 lines · +94 tokens per session 22c0ba3daf89
  2. 5d ago Changed · +91 tokens per session 401e5b0a4294
  3. 6d ago Changed · +7 lines · +368 tokens per session e5f836d6e047
  4. 8d ago Changed · -1 lines · -141 tokens per session 0265b62ce9bb
  5. 10d ago Changed · +2 lines · +121 tokens per session 2ba20ffda7c2
  6. 18d ago Changed · +1 lines · +171 tokens per session 96293d5b55a5
  7. 21d ago Changed · +1 lines · +177 tokens per session 50eb648d9124
  8. 26d ago Changed · +1 lines · +113 tokens per session fec5f1c1e782
  9. 28d ago Changed · +2 lines · +48 tokens per session 6cc1022cf306
  10. 1mo ago First seen · 24 lines · 627 tokens per session scan A 0eb175424914

Subscribe to this mod's changes

agent-harness-plugins shell.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 1,669 tokens to every session, about $0.0067 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 2026-09-15.

Related

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,257 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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.

deepseek-ai/deepseek-harness · 4,159 tokens

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).

microsoft/vscode · 2,731 tokens