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/zaxbyhub/opencode-swarm/copilot-instructionsgit clone --depth 1 https://github.com/ZaxbyHub/opencode-swarmWrote 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/zaxbyhub/opencode-swarm/copilot-instructions)<a href="https://agentmods.dev/instructions/zaxbyhub/opencode-swarm/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/zaxbyhub/opencode-swarm/copilot-instructions.svg" alt="Measured on agentmods" 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 | $0.01135 | $0.01135 |
| Opus 5 | $0.00567 | $0.00567 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
opencode-swarm 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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandatory PR Publication Protocol
These instructions apply to Copilot coding agents, Copilot custom agents, and any AI agent assigned to a GitHub issue in this repository.
Before committing, pushing, opening a pull request, updating a pull request body, marking a pull request ready, or claiming CI/merge readiness, you MUST load and follow these, in precedence order (highest authority first):
AGENTS.mddocs/engineering-invariants.md.claude/skills/commit-pr/SKILL.md— the single source of truth for publication.agents/skills/commit-pr/SKILL.md— execution adapter (routes to #3).github/skills/commit-pr/SKILL.md— Copilot discovery shim (routes to #3)
The commit-pr skill is the only approved publication workflow.
The requirements summarized below are a high-visibility mirror of
.claude/skills/commit-pr/SKILL.mdand are subordinate to it. If anything here ever differs from that skill, the skill wins — update this file to match rather than following the stale copy.
Do not run git push, gh pr create, gh pr edit, or gh pr ready until the commit-pr checklist is satisfied.
PR title requirements
Every non-release-bot PR title MUST exactly match:
<type>(<scope>): <description>
Allowed types: feat, fix, perf, revert, docs, chore, refactor, test, ci, build.
The description must be lowercase and must not end with a period. CI runs action-semantic-pull-request (the check-title job) and will fail malformed titles.
PR body requirements
Every PR body MUST include these sections, in this order:
## Summary## Invariant audit## Test plan
When the PR resolves an issue, the body's first line MUST be Closes #<issue-number>.
The ## Invariant audit section must follow the template in .claude/skills/commit-pr/SKILL.md (Step -1), listing each touched/not-touched invariant with concrete evidence.
The test plan must list the exact commands run and their result. Do not claim validation passed unless commands were actually run or remote CI completed successfully.
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.
- 5d ago First seen · 114 lines · 1,135 tokens per session scan A fd89285cbc63
opencode-swarm copilot-instructions.md is an instructions file published in the GitHub repository ZaxbyHub/opencode-swarm (462 stars, last pushed today), licensed MIT. It adds 1,135 tokens to every session, about $0.0057 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 2026-08-30.
Other instructions, from other repositories
dev-3.0 AGENTS.md
AGENTS.md instructions for h0x91b/dev-3.0, covering agents.md, response style, what is this, ui/ux work — which skill, and when and where dev3 overrides the better-family skills.
ai-driven-development AGENTS.md
AGENTS.md instructions for CodeAlive-AI/ai-driven-development, covering ai-driven development — development guide, git publishing defaults, when to create tags and releases, requires a new tag/release and does not require a new tag/release.
wmux CLAUDE.md
Claude Code instructions for openwong2kim/wmux, covering language (owner decision, 2026-07-20), skill routing, design system and versioning & release (owner decision, 2026-07-05).
meridian CLAUDE.md
Claude Code instructions for rynfar/meridian, covering claude.md, what this is, commands, code rules and module boundaries.
rosetta republish-assets-not-npm.instructions.md
Instructions for tikoci/rosetta: The republishassets workflow input is for GitHub Release assets and OCI tags only.
plan-forge version.instructions.md
Version management — Semantic versioning, auto-increment, commit-driven version bumps, release tagging.