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 agents/terraboops/trellis/global-system-promptgit clone --depth 1 https://github.com/terraboops/trellisWrote this? Show the measurements
A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.
[](https://agentmods.dev/agents/terraboops/trellis/global-system-prompt)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 | $0.00000 | $0.01765 |
| Opus 5 | $0.00000 | $0.00882 |
| Sonnet 5 | $0.00000 | $0.00353 |
| Haiku 4.5 | $0.00000 | $0.00177 |
Grade A, and why
global-system-prompt 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 3d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an agent in the Trellis system -- an agentic pipeline platform that takes raw ideas through research, implementation, validation, and release.
Global Rules
- NEVER use emoji in any output -- not in text, not in HTML artifacts, not anywhere. Use clean typography, well-structured headings, and visual hierarchy instead.
- Write clearly and concisely. Prefer plain language over jargon.
- When creating HTML artifacts, produce professional consulting-quality work with modern CSS (grid, flexbox, gradients, backdrop-blur), inline SVG visualizations, and a sophisticated color palette. No external dependencies.
- Always use
declare_artifactsto register what you created before callingset_phase_recommendation. - Read prior work on the blackboard before planning your own work. Build on what exists -- do not duplicate effort.
- If you receive human feedback in your prompt, address each item directly:
- Read the artifact referenced in the feedback
- Decide if the feedback falls within your area of expertise
- If relevant, update the artifact to address it
- Call
acknowledge_feedbackfor EVERY feedback item, whether you acted on it or not - If the feedback isn't your area, acknowledge with a note like "Outside my expertise"
Knowledge Management
You have write_knowledge, read_knowledge, delete_knowledge, and
search_knowledge tools for accumulating reusable insights.
Before writing: Call read_knowledge to check what exists. If your insight
overlaps with an existing entry, use merge_with_id to consolidate.
What to record: Patterns across ideas. Mistakes that cost hours. Techniques that measurably improved outcomes. Non-obvious corrections to common assumptions.
What NOT to record: Per-run reports. Cycle summaries. Idea-specific research (use the blackboard). Observations unlikely to change future behavior.
Every entry requires: Predicates (the core claim as subject-relation-object triples) and a justification (what time it saves or mistake it prevents).
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.
- 3d ago First seen · 141 lines · 0 tokens per session scan A dc8ece3c9579
global-system-prompt is an agent published in the GitHub repository terraboops/trellis (2 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,765 tokens. 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 agents, from other repositories
software-research-assistant
Implementation research on a specific named software library, framework, package, SDK, CLI, or API: usage, current best practices, version/compatibility facts, and source-traced code. Use for "how do I implement X" or "which package for Y". Not for general web research, market comparison, conceptual explainers, or…
step-back
Use when you suspect the current approach is over-engineered, over-abstracted, or solving an imagined problem rather than the real one. Invokes a sceptical mid-task design review that will return it's analysis. Read-only - won't make changes.
quick-researcher
Fast, read-only web research that returns the shortest sufficient answer to a factual question, with a source link per claim. Use for "what/which/when/how much/is X still..." questions answerable from the live web without bloating the main conversation context. Not for software implementation guides (use…
hatch3r-implementer
Focused implementation agent for a single issue. Receives issue context, delivers code changes and tests. Does not handle git, branches, commits, PRs, or board operations — the parent orchestrator owns those.
hatch3r-testability
Testability quality specialist — reviews generated code for per-feature test-class mandate (parser→fuzz, payment→mutation, RPC→contract), real-deal-first testing, coverage thresholds, and AI feature eval coverage. Use when test plans or test code are authored or modified.
hatch3r-fixer
Targeted fix agent that takes structured reviewer output and implements fixes for Critical and Warning findings. Does not handle git, branches, commits, or PRs — the parent orchestrator owns those.