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/trim-comments.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/trim-comments)<a href="https://agentmods.dev/instructions/cboone/agent-harness-plugins/trim-comments"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/trim-comments/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/trim-comments"><img src="https://agentmods.dev/badge/instructions/cboone/agent-harness-plugins/trim-comments.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 | $0.00499 | $0.00499 |
| Opus 5.5 | $0.00200 | $0.00200 |
| Sonnet 5.5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
agent-harness-plugins trim-comments.instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Trim comments review instructions
For repository-wide conventions, see the general Copilot instructions.
- Committing by default, never pushing, is deliberate. The skill can activate implicitly, so it stops at a local commit the user can inspect and undo;
--no-commitleaves the edits uncommitted. It commits only files that were clean before the run, directly withgit commit -- <paths>rather than through thecommitskill, whose hook, plan, and issue-reference rules would override these. Do not propose a push step, staging whole dirty files, or delegating the commit. - Committing from the working tree, then checking hashes, is deliberate. Step 6 confirms each file holds only comment edits, records its hash, commits with
git commit -- <paths>, and reports any committed content whose hash differs. A change made in the moment between the check and the commit is reported in a local, unpushed commit the user can inspect. Committing from a separate index would leave the user's index out of step withHEADfor those paths, so do not propose it. git hash-object -- "./$path"already applies clean filters. For a file argument, Git hashes the content after the path's clean filters and line-ending conversion, so it matches the blobgit commitstores; only--no-filtershashes raw bytes. Do not propose adding--path.- User-given paths are relative to the working directory on purpose. Like any command-line argument, a path the user passes is resolved from the current directory, and
git ls-files --full-nameturns the matches into root-relative paths for the rest of the workflow. Do not propose treating user arguments as root-relative; a path that matches nothing is reported, not skipped. - The
realpathequality check already rejects any symlinked component. The skill comparesrealpath "./$path"with the literal string<resolved root>/$path, not with a resolved form of it. A symlink in any component, including one pointing at an ancestor such asalias -> ., resolves to a different string, so the path is dropped. Do not report that the check misses ancestor or self-referencing 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.
- 8d ago First seen · 14 lines · 499 tokens per session scan A d10c6ff8f45a
agent-harness-plugins trim-comments.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 499 tokens to every session, about $0.0020 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 2026-10-08.
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).