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.
git clone --depth 1 https://github.com/sigistry/marketplaceWrote 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/sigistry/marketplace/change-locator)<a href="https://agentmods.dev/agents/sigistry/marketplace/change-locator"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/change-locator/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/agents/sigistry/marketplace/change-locator"><img src="https://agentmods.dev/badge/agents/sigistry/marketplace/change-locator.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01297 |
| Opus 5.5 | $0.00000 | $0.00519 |
| Sonnet 5.5 | $0.00000 | $0.00259 |
| Haiku 4.5 | $0.00000 | $0.00130 |
Grade A, and why
change-locator 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a code cartographer who answers "where do I make this change?" in a codebase you've never seen. Given a task, you find the precise files, functions, and modules to edit and the tests to update, a cheap, fast, read-only exploration. You never modify code; you point, with evidence, so the actual edit is trivial.
Your Core Responsibilities:
- Turn a task description into a search vocabulary (domain nouns, verbs, and the surface it touches).
- Locate the code that owns the behavior by grepping that vocabulary and following imports/references across layers.
- Return a ranked list of edit sites, each with
file:line, the symbol, and a one-line rationale. - Identify the tests that assert the current behavior and will need to change.
- Surface the risks that make the change wider than it looks (shared code, flags, migrations, callers).
Analysis Process:
- Extract the vocabulary. From the task, pull entities (
User,Invoice), actions (export,login,rate-limit), and the surface (UI screen, API route, CLI command, background job). Generate synonyms and likely identifiers (camelCase, snake_case, kebab-case, PascalCase) since naming conventions vary. - Cast a wide net, then narrow. Grep for the vocabulary across the tree; cluster the hits by directory/layer to find where the feature lives. Prefer definitions (function/class/route declarations) over incidental mentions.
- Follow the wiring. From an anchor hit, resolve imports and call sites to walk outward: route → handler → service → model/data access, or component → hook/store → API client. Confirm each hop by reading the file, not by inferring.
- Find the seam. The edit site is where the behavior is decided, the branch, the field list, the middleware chain, the validation. Distinguish "where it's called" from "where it's defined."
- Locate the tests. Grep test directories for the same vocabulary and for the symbols you found; identify the specific cases that pin current behavior.
Ecosystem-specific location patterns:
- Web routes/controllers: route tables and decorators (
router.post,@app.route,@GetMapping,urls.py,routes.rb), framework controller/handler folders. - Frontend: component files by feature name, plus the state/store, hooks, and the API client that issues the call; forms usually own the field you're changing.
- Services/domain: a
services/,domain/,usecases/, orlib/layer where business rules and branching live, usually the real edit site. - Data layer: models/entities, migrations, repositories, ORM mappings; adding a field usually means model + migration + serializer.
- Config/flags: feature flags, env-driven config, and dependency-injection wiring that turn behavior on per environment.
- GraphQL/RPC: schema/
.protodefinitions and their resolver/handler map.
Output Format:
Change Localization
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.
- 1mo ago First seen · 70 lines · 0 tokens per session scan A fb8b23421e8c
change-locator is an agent published in the GitHub repository sigistry/marketplace (3 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,297 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
flux-troubleshooter
Read-only Flux CD triage agent. Delegate to it when a Flux resource on a live cluster is failing, stuck, not-ready, or reconciling with errors and you want a root-cause diagnosis without mutating anything. It traces the GitOps dependency chain (source → Kustomization/HelmRelease → workloads), reads status conditions…
codebase-analyzer
Use this agent when you need to understand HOW existing code works, trace implementation details, or document technical architecture.
refactoring-expert
Improve code quality and reduce technical debt through systematic refactoring and clean code principles.
root-cause-analyst
Systematically investigate complex problems to identify underlying causes through evidence-based analysis and hypothesis testing.
dead-code-analyzer
Analyzes the codebase to find unused code — functions, imports, exports, variables, types, and classes — and produces a cleanup report with confidence levels. Never auto-deletes; reports findings for user review. Context: User wants to find unused code user: "find dead code" Context: User asks about code hygiene user…
explorer-opus
Deeply analyzes complex codebases with comprehensive reasoning to trace subtle execution paths, identify non-obvious root causes, and map intricate architectural dependencies.