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 skills add neuromechanist/research-skills --skill install-user-instructionsgit clone --depth 1 https://github.com/neuromechanist/research-skillsWrote 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/skills/neuromechanist/research-skills/install-user-instructions)<a href="https://agentmods.dev/skills/neuromechanist/research-skills/install-user-instructions"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/install-user-instructions/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/skills/neuromechanist/research-skills/install-user-instructions"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/install-user-instructions.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 | $0.00087 | $0.00848 |
| Opus 5 | $0.00044 | $0.00424 |
| Sonnet 5 | $0.00017 | $0.00170 |
| Haiku 4.5 | $0.00009 | $0.00085 |
Grade C, and why
install-user-instructions scanned grade C with 1 finding 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 13d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
`<!-- research-skills:global-instructions:start -->` and How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Install User Instructions
Install shared personal defaults at each selected system's supported user surface without overwriting custom content or copying global rules into every repository.
Workflow
- Detect available systems with read-only checks (
command -vplus existing target files). Do not infer that every detected system should be modified. - Ask the user which of Claude Code, Codex, Copilot CLI, and Cursor to configure. This selection is required before any user-home write.
- Read
references/platform-paths.mdfor the selected systems. Resolve documented home overrides before default paths. - Choose the instruction content:
- use
assets/global-instructions.mdfor the project defaults; - use a user-supplied file with
--templatewhen requested; - never silently copy a repository's project-specific instructions into user scope.
- use
- Run
scripts/install_user_instructions.py --systems <csv>without--apply. This is the mandatory dry-run and diff preview. - Show every destination and diff. For Cursor, show the copy/paste block for Cursor Settings > Rules; do not invent a filesystem destination.
- Ask for confirmation of the exact selected destinations and changes.
- After confirmation, rerun with
--apply. Writing outside the workspace may require the runtime's normal filesystem approval. - Verify each selected system using the command or UI check in
references/platform-paths.md. - Audit the current repository for duplicated general rules. Report exact duplicates or conflicts, but remove project content only with separate user approval.
Non-destructive contract
- Manage only the block between
<!-- research-skills:global-instructions:start -->and<!-- research-skills:global-instructions:end -->. - Preserve all content outside the managed block byte-for-byte.
- Fail on unmatched or repeated markers instead of guessing.
- Default to preview mode.
--applyis required for writes. - Write only explicitly selected systems.
- Keep Cursor manual until its official User Rules surface exposes a stable, supported file path.
- Keep general personal defaults at user scope. Repository
AGENTS.md,CLAUDE.md,.github/copilot-instructions.md, and.cursor/rulescontain only project facts or system-specific/path-scoped deltas. - Do not duplicate shared project rules in
CLAUDE.md; importAGENTS.mdand append Claude-only deltas.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago First seen · 91 lines · 87 tokens per session scan C 3f324f235bae
install-user-instructions is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 10d ago), licensed BSD-3-Clause. It adds 87 tokens to every session and 848 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
releasing-godot-prompter
Use when cutting a GodotPrompter release or bumping its version — the version-bump sequence, tag-triggered workflow, and the marketplace manifests that must follow.
obsidian-workout-export
Export workout data to an Obsidian-formatted Markdown file. Always trigger immediately when the user types "owd". Also trigger on "export workout", "obsidian workout", "save workout to obsidian", or related requests to export workout data into Obsidian. Read the current conversation first before searching prior…
skill-iterative-loop
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence.
screen-detox
A habit-change framework for reducing non-work screen use such as social media, short videos, games, and endless scrolling.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
file-organizer
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.