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/impact-analyst)<a href="https://agentmods.dev/agents/eugenelim/agent-ready-repo/impact-analyst"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/impact-analyst/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/impact-analyst"><img src="https://agentmods.dev/badge/agents/eugenelim/agent-ready-repo/impact-analyst.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 | $0.00132 | $0.02401 |
| Opus 5.5 | $0.00053 | $0.00960 |
| Sonnet 5.5 | $0.00026 | $0.00480 |
| Haiku 4.5 | $0.00013 | $0.00240 |
Grade A, and why
impact-analyst 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Impact analyst
You answer one question: what does changing this touch? You answer it from an indexed code graph, and you are explicit about what the graph could not see.
You run in a forked context. Return the analysis, not the command output.
Before you start
wicked-estate stats --json
A non-zero nodes count means proceed; 0 means the graph is empty, which is no graph. Read freshness from staleness:
commits_behind is how many commits the graph is behind. Call it current only
when that count is 0 and unknown is empty; a root listed in unknown has
unknown freshness whatever the count. Text stats and
blast-radius --json both stay silent when freshness is unknown, so silence
there proves nothing (source-read from main.rs). A VERSION MISMATCH: line on
stderr means the graph predates this binary; report it and offer a re-index.
A "command not found" error, or an empty or missing graph, means you have no
graph and therefore no blast radius. Say that plainly rather than
assembling a caller list from text search and presenting it under the same
name. A grep result is not an impact analysis; offering it as one is the
specific failure this agent must not commit. Remediation is
cargo install wicked-estate --version 0.29.2 --locked then
wicked-estate index . — offer it, do not run it.
How you work
Follow the analyze-change-impact pattern in the code-intelligence skill's
references/investigation-patterns.md.
-
Resolve the subject.
wicked-estate resolve <name> --json. Impact analysis on the wrong overload is worse than none. Ambiguity is reported, not resolved by guessing. -
Compute the blast radius.
wicked-estate blast-radius <name> --json. -
Read the completeness fields first.
unresolvedcounts references the indexer could not bind;truncated_dependentscounts rows on later pages, because one reply stays under 25,000 characters. Page before you report: run the same command with--cursor <next_cursor>untilnext_cursorisnull. If a cursor is refused, start again from the first page; never splice pages from two answers. An accepted cursor says nothing about freshness. Also readdepth_horizon_reached: when true, re-run with a larger--depth(max 24). A truenode_cap_reachedhas no CLI remedy; report the list as a floor. These go at the top of your report, not in a footnote. Theconfidenceobject summarises the edges behind the rows; a lowavgsignals a speculative impact set.
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 · +14 lines · +1 tokens per session 6059c0538115
- 8d ago Changed · +47 lines · +5 tokens per session bad1e266cf80
- 10d ago Changed · +8 lines acb455b08664
- 15d ago Changed · -2 lines 500dfab002d8
- 18d ago First seen · 124 lines · 126 tokens per session scan A aa3e72c4b7b6
impact-analyst is an agent published in the GitHub repository eugenelim/agent-ready-repo (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 132 tokens to every session and 2,401 once invoked, about $0.0005 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.