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 skills add JBorgia/signaltree --skill guardrailsgit clone --depth 1 https://github.com/JBorgia/signaltreeWrote 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/skills/jborgia/signaltree/guardrails)<a href="https://agentmods.dev/skills/jborgia/signaltree/guardrails"><img src="https://agentmods.dev/badge/skills/jborgia/signaltree/guardrails/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jborgia/signaltree/guardrails"><img src="https://agentmods.dev/badge/skills/jborgia/signaltree/guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00092 | $0.01179 |
| Opus 5.5 | $0.00037 | $0.00472 |
| Sonnet 5.5 | $0.00018 | $0.00236 |
| Haiku 4.5 | $0.00009 | $0.00118 |
Grade A, and why
signaltree-guardrails 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 2mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using @signaltree/guardrails
Dev-only enhancer — instruments every update() call, tracks hot paths, watches memory growth, runs rule registry against each change. In production builds, package exports swap to a noop via the production export condition — the enhancer call stays in source but costs zero. If bundler doesn't set production condition, guard manually: isDevMode() ? guardrails({...}) : ((t) => t).
Install (dev dependency):
npm install --save-dev @signaltree/guardrails
Peer: @signaltree/core ^9. Don't install @signaltree/shared — private workspace package; npm will fail to resolve it.
Basic — performance budget + console warnings:
import { signalTree } from '@signaltree/core';
import { guardrails } from '@signaltree/guardrails';
interface AppState {
items: unknown[];
ui: { search: string };
}
const tree = signalTree<AppState>({ items: [], ui: { search: '' } }).with(
guardrails({
mode: 'warn', // 'warn' | 'throw' | 'silent'
budgets: {
maxUpdateTime: 16, // ms per update
},
hotPaths: { enabled: true, threshold: 10, topN: 5 },
reporting: { console: true, interval: 5000, maxIssuesPerReport: 20 },
})
);
Memory-leak detection + intent suppression:
const tree = signalTree(initial).with(
guardrails({
memoryLeaks: {
enabled: true,
checkInterval: 5000,
retentionThreshold: 200,
growthRate: 0.25,
},
suppression: {
autoSuppress: ['hydrate', 'reset', 'bulk', 'migration', 'time-travel', 'serialization'], // values from intent/source that silence budget warnings
respectMetadata: true,
},
})
);
Valid autoSuppress values (union of intent and source channels that suppression respects): 'hydrate', 'reset', 'bulk', 'migration', 'time-travel', 'serialization'.
Valid intent values on UpdateMetadata: 'user', 'system', 'hydrate', 'reset', 'bulk', 'migration'.
Valid source values on UpdateMetadata: 'user', 'system', 'devtools', 'time-travel', 'serialization'.
Custom rule (rules run per changed leaf; context.path = string[], context.value = new leaf value; test returns true when rule fires):
import { guardrails, rules } from '@signaltree/guardrails';
const tree = signalTree({ ui: { when: '' } }).with(
guardrails({
customRules: [
rules.noDeepNesting(6),
rules.noSensitiveData(),
{
name: 'no-date-strings-in-ui',
severity: 'warning',
test: (context) => context.path[0] === 'ui' && typeof context.value === 'string' && /^\d{4}-\d{2}-\d{2}/.test(context.value as string),
message: (context) => `ui path "${context.path.join('.')}" holds a date string; use Date in state.`,
},
],
})
);
Built-in rules from rules registry: rules.noDeepNesting(n), rules.noFunctionsInState(), rules.maxPayloadSize(kb), rules.noSensitiveData().
Pre-baked factory trees (@signaltree/guardrails/factories): createFeatureTree, createAngularFeatureTree, createAppShellTree (strict 4ms budget), createPerformanceTree, createTestTree (mode: 'throw'). Accept (signalTree, initial):
import { createAppShellTree } from '@signaltree/guardrails/factories';
const shell = createAppShellTree(signalTree, initial);
Use mode: 'throw' in test harnesses to fail tests on over-budget updates. Use P50/P95/P99 reporting via reporting.customReporter: (report) => fetch('/telemetry', ...).
Gotchas:
- Don't install
@signaltree/shared— private package, npm resolution fails. maxTreeDepthcounts object nesting depth, not path length. A 12-deep branch trips amaxTreeDepth: 10budget even if rest of tree is flat.trackDownstream: truewalks consumer computeds — more accurate, noticeably slower. Only enable when chasing re-computation cycles.- Memory-leak checks use
structuredClonewhen available; falls back to JSON clone (skips non-serializable values). - Never apply in production without relying on
productionexport condition orisDevMode()guard.
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.
- 2mo ago First seen · 105 lines · 92 tokens per session scan A c1ea561ef67c
signaltree-guardrails is a skill published in the GitHub repository JBorgia/signaltree (22 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,179 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.
diagnosing-missing-recordings
Diagnoses why a session recording is missing or was not captured. Use when a user asks why a session has no replay, why recordings aren't appearing, or wants to troubleshoot session replay capture issues for a specific session ID or across their project. Covers SDK diagnostic signals, project settings, sampling…