tracer

tracer is an agent for Claude Code from alphabravo-oss/guild. It costs 26 tokens per session (7,206 once invoked), scanned A, original, MIT.

A read-only check that traces functions, endpoints, and data flows from a specification through the codebase.

In plain words
What is it for?
Use it to verify that specified symbols exist, are reachable, and are connected to the expected entry points.
Why use it?
A function or API endpoint may exist in files but never be connected to the part of the application that should use it. This check looks for missing or incorrect wiring.

Agent for Claude Code

Written for Claude Code: effort in frontmatter. Also seen: model in frontmatter; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the foundry plugin — 4 skills, 4 commands, 12 agents shipped together

Good fit Use it to verify that specified symbols exist, are reachable, and are connected to the expected entry points.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add alphabravo-oss/guild
Claude Code
/plugin install foundry

Made for: Claude Code.

Or install foundry, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 12 agents.

Wrote 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.

agentmods badge for tracer

README.md
[![agentmods](https://agentmods.dev/badge/agents/alphabravo-oss/guild/tracer/github.svg)](https://agentmods.dev/agents/alphabravo-oss/guild/tracer)
Your own site
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/tracer"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/tracer/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.

agentmods 80×15 button for tracer

Your own site · 80×15
<a href="https://agentmods.dev/agents/alphabravo-oss/guild/tracer"><img src="https://agentmods.dev/badge/agents/alphabravo-oss/guild/tracer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00026 $0.07206
Opus 5.5 $0.00010 $0.02882
Sonnet 5.5 $0.00005 $0.01441
Haiku 4.5 $0.00003 $0.00721

Measured 1mo ago against content hash 0c5890e11d89, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

plugins/foundry/agents/tracer.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tracer Agent

Deterministic wiring verification using Serena LSP tools. Traces every function, endpoint, and data flow declared in the spec to verify it exists, is called, and implements the spec correctly.

Role

You are a deterministic wiring verification agent. You trace symbols through the codebase to prove that every declared symbol exists, is reachable from its expected entry point, and implements what the spec requires. You are read-only — never modify code.

Serena LSP tools are the authoritative resolution method. They are not always present: they require a shared daemon on localhost:9121 that many installs do not run. When they are absent the trace still runs — a degraded trace is worth more than no trace — but it runs under a hard limit that follows from what search can and cannot establish:

  • grep can disprove. If a declared symbol appears nowhere, it is absent. Negative verdicts (MISSING, UNWIRED, WRONG) are legitimate from a grep trace.
  • grep cannot confirm. A textual match is not proof that a symbol resolves, is reachable, or is called with the arguments its contract declares. No symbol may be reported WIRED on grep evidence — it is NOT_VERIFIED, cause SERENA_UNAVAILABLE.

Which mode you ran in is itself a reportable fact: emit method on every report. See Step 0.

Input

You will receive:

  • Spec file or casting scope with observable truths
  • Cycle number (for regression detection across iterations)
  • Previous trace results (if any)
  • FOUNDRY_SERENA_HEALTH token from the run's F0 Serena preflight, if the lead passed it (recorded at foundry-archive/{run}/handoffs.jsonl under event: "serena_preflight"). It names the daemon's state at run start — cite it when you emit NOT_VERIFIED.

Procedure

0. Serena Availability Gate

Before verifying anything, confirm the Serena LSP tools actually answer. Issue one real call — get_symbols_overview on a file you know exists, or find_symbol on any declared symbol — and check the result.

Read the full file on GitHub · 335 lines

Changes

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.

  1. 1mo ago Changed · +72 lines 0c5890e11d89
  2. 1mo ago First seen · 263 lines · 26 tokens per session scan A 3c4501758e47

Subscribe to this mod's changes

tracer is an agent published in the GitHub repository alphabravo-oss/guild (2 stars, last pushed 11d ago), licensed MIT. It adds 26 tokens to every session and 7,206 once invoked, about $0.0001 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 2026-09-04.

Related

Other agents, from other repositories

build-failure-analyst

Expert build-failure analyst for .NET / MSBuild repositories. Invoke when a build produced a binary log (.binlog) and you need to identify the root cause(s) of failure, group related errors, and propose concrete fixes. Queries the binlog live through the binlog-mcp MCP server (containerised — see the calling…

dotnet/skills · 108 tokens

swiftui-performance-analyzer

Use this agent when the user mentions SwiftUI performance, janky scrolling, slow animations, or view update issues — expensive bodies, formatters, whole-collection dependencies, and missing lazy containers.

CharlesWiltgen/Axiom · 45 tokens

predictive-analyst

Precognition agent. Analyzes code changes to predict impact, regressions, and conflicts BEFORE they happen. Uses dependency graphs and historical data.

softspark/ai-toolkit · 35 tokens

gentle-ai-explore

Read-only exploration and mapping for generic non-SDD work.

Gentleman-Programming/gentle-pi · 18 tokens

silent-failure-hunter

Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. Invoke it after work involving error handling, catch blocks, fallback logic, or any code that could suppress errors. See "When to invoke" in the agent body for…

nota-america/forgecat-agent-profiles · 67 tokens

code-reviewer-bug

name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.

zxpmail/ReqForge · 0 tokens