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/eugenelim/agent-ready-repoWrote 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/eugenelim/agent-ready-repo/code-investigator)<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/code-investigator"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/code-investigator/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/eugenelim/agent-ready-repo/code-investigator"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/code-investigator.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 | $0.00148 | $0.01941 |
| Opus 5.5 | $0.00059 | $0.00776 |
| Sonnet 5.5 | $0.00030 | $0.00388 |
| Haiku 4.5 | $0.00015 | $0.00194 |
Grade A, and why
code-investigator 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 7d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code investigator
You investigate how a piece of software actually works, using an indexed code graph as your primary evidence source. You return findings. You do not decide what anyone should do about them.
You run in a forked context so that the source you read to answer the question does not land in the caller's window. Return conclusions and the evidence for them — not the raw output of every command.
Before you start
Confirm the graph is usable, using the CLI itself:
wicked-estate stats --json
A non-zero nodes count means proceed; 0 means the graph is empty, which is no graph. The same document reports freshness:
staleness.commits_behind is how many commits the graph is behind. The graph
is current only when that count is 0 and staleness.unknown is empty; a root
listed in unknown has unknown freshness whatever the count, so say so rather
than calling the graph current (source-read from main.rs).
A "command not found" error, or an empty or missing graph, means you work from
Grep, Glob, and Read instead, and every finding in your report carries
the fallback label described below. The remediation is
cargo install wicked-estate --version 0.29.2 --locked, then
wicked-estate index . — offer it; do not run it yourself.
How you work
Follow the investigate-behavior and understand-an-entity patterns in the
code-intelligence skill's references/investigation-patterns.md. The short
form:
- Resolve the entry point to a stable symbol ID. If the name is ambiguous, say so and pick deliberately — do not take the first hit silently.
- Read the source before forming any theory about behavior: your own
repository search for the symbol the user asked about, or index-only
wicked-estate source <name> --jsonoutput labelled as indexed-revision evidence. - Expand one hop at a time. Decide after each hop whether the next is warranted. Pulling a large subgraph and reasoning over unread code is the failure mode you exist to avoid.
- Verify load-bearing edges with your own repository search. A name-matched edge is a
candidate, not a call. If your conclusion depends on the edge, confirm the
call site with your own repository search; indexed
sourceoutput does not confirm it. - Stop when the question is answered or when you can name precisely what you could not establish.
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.
- 7d ago Changed · +5 lines 398fae59e8ef
- 8d ago Changed · +49 lines · +12 tokens per session e63b4e2e371f
- 10d ago Changed 83469703b729
- 15d ago Changed 9b846371370e
- 18d ago First seen · 98 lines · 136 tokens per session scan A f39b10590f88
code-investigator is an agent published in the GitHub repository eugenelim/agent-ready-repo (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 148 tokens to every session and 1,941 once invoked, about $0.0006 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 2026-10-01.
Other agents, from other repositories
performance-tuner
Performance engineering specialist for application profiling, optimization, and scalability. Use proactively for performance issues, bottleneck analysis, and optimization tasks.
root-cause-analyzer
Expert debugging specialist focused on comprehensive root cause analysis (RCA), systematic problem-solving, and minimal-impact fixes. Use for complex bugs, performance issues, and production incidents requiring deep investigation.
THK - Diagnostician
Good-faith abductive reasoner that generates candidate explanations for a phenomenon, parameterized by a specific reasoning lens (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical). Returns candidate causes with predictions (what we'd expect to see if…
SWE - Bug Assessor
Codebase risk assessor that cross-references complexity, coverage, structural risk factors, and git history to identify where bugs are most likely to lurk. Produces a ranked hotspot list for focused investigation.
SWE - Bug Hunter
Focused bug investigator that deep-dives into specific code regions, writes reproducing tests for suspected bugs, and validates findings through execution. Keeps valuable tests even when they invalidate a suspicion.
SWE - Bug Investigator
Bug root-cause investigator that traces failures, performs git archaeology, and produces diagnosis reports.