Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/danshapiro/kilroynpx agentmods add skills/danshapiro/kilroy/investigating-kilroy-runsWrote 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/skills/danshapiro/kilroy/investigating-kilroy-runs)<a href="https://agentmods.dev/skills/danshapiro/kilroy/investigating-kilroy-runs"><img src="https://agentmods.dev/badge/skills/danshapiro/kilroy/investigating-kilroy-runs/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/skills/danshapiro/kilroy/investigating-kilroy-runs"><img src="https://agentmods.dev/badge/skills/danshapiro/kilroy/investigating-kilroy-runs.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 | $0.00114 | $0.03267 |
| Opus 5 | $0.00057 | $0.01633 |
| Sonnet 5 | $0.00023 | $0.00653 |
| Haiku 4.5 | $0.00011 | $0.00327 |
Grade A, and why
investigating-kilroy-runs scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS "$CXDB_URL/health" || curl -fsS "$CXDB_URL/healthz" How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigating Kilroy Runs
To inspect a run quickly and produce a precise diagnosis, follow this workflow.
Resolve Run Root
- To resolve run root with highest confidence, start from an explicit
--logs-rootpath when provided. - To infer run root when no path is provided, locate the newest run under
~/.local/state/kilroy/attractor/runs. - To keep later commands consistent, treat that directory as
RUN_ROOT.
RUNS="$HOME/.local/state/kilroy/attractor/runs"
RUN_ID="$(find "$RUNS" -mindepth 1 -maxdepth 1 -type d -printf '%T@ %f\n' | sort -nr | awk 'NR==1 {id=$2} END {print id}')"
RUN_ROOT="$RUNS/$RUN_ID"
echo "$RUN_ID"
For a quick check of the newest run without manually resolving RUN_ROOT, use:
./kilroy attractor status --latest --json
CXDB: Launch, UI, and Query
To get CXDB connection details, start with manifest.json, then fall back to run_config.json and live artifacts when fields are missing:
CXDB_URL="$(jq -r '.cxdb.http_base_url // empty' "$RUN_ROOT/manifest.json")"
CONTEXT_ID="$(jq -r '.cxdb.context_id // empty' "$RUN_ROOT/manifest.json")"
if [ -z "$CXDB_URL" ] && [ -f "$RUN_ROOT/run_config.json" ]; then
CXDB_URL="$(jq -r '.cxdb.http_base_url // empty' "$RUN_ROOT/run_config.json")"
fi
if [ -z "$CONTEXT_ID" ] && [ -f "$RUN_ROOT/live.json" ]; then
CONTEXT_ID="$(jq -r '.context_id // empty' "$RUN_ROOT/live.json")"
fi
if [ -z "$CONTEXT_ID" ] && [ -f "$RUN_ROOT/checkpoint.json" ]; then
CONTEXT_ID="$(jq -r '.context_id // empty' "$RUN_ROOT/checkpoint.json")"
fi
echo "cxdb_url=$CXDB_URL context_id=$CONTEXT_ID"
To make sure CXDB is available and to print the UI endpoint, run:
./scripts/start-cxdb.sh
UI_LINE="$(./scripts/start-cxdb-ui.sh)"
echo "$UI_LINE" # prints: cxdb_ui=http://...
CXDB_UI="${UI_LINE#cxdb_ui=}"
Use the endpoint printed by start-cxdb-ui.sh (cxdb_ui=...) as the source of truth. To open the UI in a browser when needed, run:
KILROY_CXDB_OPEN_UI=1 ./scripts/start-cxdb-ui.sh
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 331 lines · 114 tokens per session scan A a8d14848303f
investigating-kilroy-runs is a skill published in the GitHub repository danshapiro/kilroy (219 stars, last pushed 4mo ago), licensed MIT. It adds 114 tokens to every session and 3,267 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.