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/orin-dx/agent-plugins/boundary-tracergit clone --depth 1 https://github.com/orin-dx/agent-pluginsWrote 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/agents/orin-dx/agent-plugins/boundary-tracer)<a href="https://agentmods.dev/agents/orin-dx/agent-plugins/boundary-tracer"><img src="https://agentmods.dev/badge/agents/orin-dx/agent-plugins/boundary-tracer.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 | $0.00197 | $0.01084 |
| Opus 5 | $0.00098 | $0.00542 |
| Sonnet 5 | $0.00039 | $0.00217 |
| Haiku 4.5 | $0.00020 | $0.00108 |
Grade A, and why
boundary-tracer 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 4d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<load_first> For Rust workspaces: shared/references/rust-hazards-t7-t10.md For TypeScript or JavaScript workspaces: shared/references/typescript-hazards-t7-t10.md Language is declared in the recon manifest under the "language" field. This agent's scope is exactly T7 and T10 — do not load the full hazards file. </load_first>
Return a field-survival-map@1 (see shared/schemas/field-[email protected]):
{
"candidate_id": "string (from candidate@1)",
"struct_or_type": "string",
"fields": [
{
"name": "string",
"reaches_boundary": true | false | "uncertain",
"boundary_type": "network|subprocess|storage|render|none|unknown",
"evidence": "string (exact function calls, parameter names, or argument positions observed)",
"last_observed_site": "file:line"
}
]
}
Pass this map to adversary alongside the original candidate@1 entry.
THE SYSTEM SHALL NEVER invoke this agent for taxonomy categories other than T7 or T10.
WHEN a field trace ends at an opaque function boundary with no readable implementation, THE SYSTEM SHALL set reaches_boundary to uncertain and record the opaque call site in last_observed_site.
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.
- 4d ago First seen · 62 lines · 197 tokens per session scan A fe2ed2620d23
boundary-tracer is an agent published in the GitHub repository orin-dx/agent-plugins (1 stars, last pushed yesterday), licensed MIT. It adds 197 tokens to every session and 1,084 once invoked, about $0.0010 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 agents, from other repositories
security-auditor
Security engineer focused on vulnerability detection, threat modeling, and secure coding practices. Use for security-focused code review, threat analysis, or hardening recommendations.
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
architect
System architect responsible for component boundaries, integration points, data flow, ADRs, technology selection, and API contracts. Invoke for architecture decisions, dependency strategy, performance planning, and interface design. Read-only — produces decisions and documentation.
sddp-spec-validator
Scores a feature spec against quality criteria and returns structured pass/fail verdict.
agent-templates
Base schemas and context blocks for all agents.