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/ai-hydro/swatplus-builder/tool-surfacegit clone --depth 1 https://github.com/AI-Hydro/swatplus-builderWhat 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 | $0.00627 |
| Opus 5 | $0.00000 | $0.00313 |
| Sonnet 5 | $0.00000 | $0.00125 |
| Haiku 4.5 | $0.00000 | $0.00063 |
Grade A, and why
tool-surface 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tool surface
The MCP server exposes 13 typed tools in three tiers. The names below are
the exact tool names registered in src/swatplus_builder/mcp/server.py.
Tier 0 — Canonical governed workflow (2 tools)
This is the entry point for "model gauge X". It is the only MCP path that produces a claim-governed evidence bundle.
| Tool | Purpose |
|---|---|
run_workflow |
launch the canonical workflow (build → run → lock → calibrate → verify → evidence bundle) for a USGS gauge ID as a detached background process; returns immediately with out_dir, pid, and the equivalent_cli string for reproducibility |
workflow_status |
poll a launch: running / completed / failed, with evidence_summary_path and blocker class once finished |
A full run takes tens of minutes — the background launch keeps the MCP call
fast, and the agent polls workflow_status between other work. On completion,
summarize only from the evidence bundle.
Tier 1 — Basin workflow (8 tools)
| Tool | Purpose |
|---|---|
build_project |
validate a basin spec and write a build manifest (does not build a runnable project — use run_workflow) |
run_basin |
run the lower-level pipeline orchestrator (no evidence bundle — prefer run_workflow) |
calibrate |
standalone pySWATPlus-bridge calibration (non-authoritative path) |
propose_parameters |
suggest calibration parameters for a basin |
compare_runs |
compare metrics across runs |
query_artifacts |
look up artifacts from a run directory |
diagnose_failure |
structured diagnosis of a failed run |
validate |
validate a project / run against expectations |
Tier 2 — Benchmark / readiness (3 tools)
| Tool | Purpose |
|---|---|
lock_benchmark |
seal a baseline with hashes (start of the locked protocol) |
locked_calibrate |
calibrate against a lock and verify |
readiness_table |
summarize lock/calibration/verification across basins |
How tools enforce governance
The tools are deliberately typed and narrow. An agent cannot reach past them to, say, hand-edit a metric into the evidence bundle or promote a claim tier. Claim tiers are emitted by the package from gate results; the tools expose the operations (build, run, calibrate, verify, query) but not the authority to override an evidence-backed decision.
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.
- 2d ago First seen · 57 lines · 0 tokens per session scan A 15ab27727882
tool-surface is an agent published in the GitHub repository AI-Hydro/swatplus-builder (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 627 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.