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 agentmods add instructions/semanticash/cli/copilot-instructionsgit clone --depth 1 https://github.com/semanticash/cliWhat 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 | $0.00309 | $0.00309 |
| Opus 5 | $0.00154 | $0.00154 |
| Sonnet 5 | $0.00062 | $0.00062 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
cli copilot-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 yesterday.
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
Review pull requests for correctness, regressions, and missing tests before style concerns.
Semantica is a Go CLI that captures AI coding activity, stores repo-local state in .semantica/lineage.db, integrates with git hooks, and computes commit attribution from hook events and checkpoint data. Prioritize findings in these areas:
- git hook behavior and commit lifecycle correctness
- attribution accuracy and checkpoint window boundaries
- SQLite locking, migrations, and repo-local state consistency
- file path normalization, repo-relative paths, and untracked/non-ignored file handling
- subprocess, shell, auth, and remote push safety
When reviewing:
- Prefer bug-risk comments over style or naming suggestions.
- Call out missing or weak tests for hook flows, attribution logic, SQLite behavior, workflows, and release packaging.
- If SQL queries, schema, or generated DB code change, check that generated files stay in sync.
- If a change affects CLI behavior, installation, release packaging, or GitHub reporting, check whether docs or changelog updates are needed.
- Avoid low-value commentary about formatting, minor refactors, or personal preference unless it hides a real bug.
Repository-specific notes:
- Generated SQLite query code lives under
internal/store/sqlite/db/. - Release behavior is driven by
.goreleaser.yamland.github/workflows/. - The most sensitive areas are
internal/service/,internal/hooks/,internal/store/sqlite/,internal/git/, and workflow/config changes under.github/.
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.
- yesterday First seen · 24 lines · 309 tokens per session scan A 343a04b9e9f6
cli copilot-instructions.md is an instructions file published in the GitHub repository semanticash/cli (3 stars, last pushed 3d ago), licensed MIT. It adds 309 tokens to every session, about $0.0015 per session on Opus 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.
Other instructions, from other repositories
OpenSunstar AGENTS.md
Instructions for alisunstar/OpenSunstar, covering agents.md — ai agent integration guide, 商业控制面隔离与发版边界, cli 治理与编排工具 (os), 全局选项 and 错误输出格式.
ctxmem AGENTS.md
Instructions for DoppiaG93/ctxmem: This repo has a ctxmem memory: a shared, git-committed record of decisions and code context. Treat it as your first source of truth and keep it correct. Follow this loop on EVERY request, without being asked.
momo-code AGENTS.md
AGENTS.md instructions for momozi1996/momo-code, covering agents.md -- project agent instructions, how to work with this codebase, getting started, making changes and quality gates (enforced).
momo-code CLAUDE.md
Claude Code instructions for momozi1996/momo-code, covering claude.md -- agent working agreement, project context, code patterns, testing and commit style.
repomemory CLAUDE.md
Instructions for DanielGuru/repomemory, covering repomemory — agent instructions, repository memory (repomemory), what this is, architecture and key technical decisions.
repomemory AGENTS.md
Instructions for DanielGuru/repomemory, covering repomemory — instructions for ai coding agents, project overview, repository structure, how to build and test and key architecture decisions.