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/bonnguyenitc/specship/copilot-instructionsgit clone --depth 1 https://github.com/bonnguyenitc/specshipWrote 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/bonnguyenitc/specship/copilot-instructions)<a href="https://agentmods.dev/instructions/bonnguyenitc/specship/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/bonnguyenitc/specship/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 5.1 | $0.00393 | $0.00393 |
| Opus 5 | $0.00197 | $0.00197 |
| Sonnet 5 | $0.00079 | $0.00079 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
specship 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.
What it actually says
Agent feature workflow (specship)
For any non-trivial change, follow .specship/skills/WORKFLOW.md and the
per-stage playbooks in .specship/skills/ss-<stage>/SKILL.md.
Stages (every skill folder is ss--prefixed):
ss-spec→ understand the request →tasks/TASK-<ID>/spec.mdss-plan→ design steps →tasks/TASK-<ID>/plan.mdss-coding→ implement (TDD or conventional), tickS#ss-review→ run the full gate, verify everyAC#→tasks/TASK-<ID>/review.mdss-debug→ when a defect appears, log it intasks/TASK-<ID>/debug.md, fix, resumess-ship→ autopilot: given a feature request, run spec → plan → coding → review end-to-endss-resume-task,ss-pause-task,ss-archive-task→ task lifecycle without losing pipeline statess-research→ answer an external-fact question with the strongest search tool available (specialized MCP search first) → complete cited report indocs/research/
The ss- prefix names skills only — stage:/artifacts: values in task.md
stay unprefixed (spec, plan, coding, review, debug, done).
Maintain shared state in tasks/TASK-<ID>/: read task.md first, update it last,
keep IDs stable, and timestamp every log entry as YYYY-MM-DD HH:MM +TZ using
date. Only the pipeline stages and lifecycle skills write to tasks/. Don't
run git add/commit/push unless asked.
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 · 24 lines · 393 tokens per session scan A 8d687fb3ccac
specship copilot-instructions.md is an instructions file published in the GitHub repository bonnguyenitc/specship (2 stars, last pushed 27d ago), licensed MIT. It adds 393 tokens to every session, about $0.0020 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
open-swe CLAUDE.md
Claude Code instructions for langchain-ai/open-swe, a project described as: An Open-Source Asynchronous Coding Agent.
baguette CLAUDE.md
Claude Code instructions for tddworks/baguette, covering claude.md, tdd is non-negotiable (read this first), naming the abstractions, splitting an adapter that wraps 3rd-party i/o and coverage target.
cyrus copilot-instructions.md
Copilot instructions for cyrusagents/cyrus: Note, there is a need to maintain the use of '--print' when running the claude exec commands because that is what makes it non-interactive.
open-vibe-island AGENTS.md
AGENTS.md instructions for Octane0411/open-vibe-island, covering agents, goal, required workflow, commit policy and safety rules.
cyrus CLAUDE.md
Claude Code instructions for cyrusagents/cyrus, covering claude.md, project overview, how cyrus works, example interaction and test drives.
hello-halo CLAUDE.md
Claude Code instructions for openkursar/hello-halo: No hardcoded text. Use t('English text').