Borrowing it
Nothing to install: this file belongs to d-kuro/kirocc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/d-kuro/kirocc/main/.claude/skills/kiro-capture/SKILL.mdgit clone --depth 1 https://github.com/d-kuro/kiroccWrote 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/d-kuro/kirocc/kiro-capture)<a href="https://agentmods.dev/skills/d-kuro/kirocc/kiro-capture"><img src="https://agentmods.dev/badge/skills/d-kuro/kirocc/kiro-capture/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/d-kuro/kirocc/kiro-capture"><img src="https://agentmods.dev/badge/skills/d-kuro/kirocc/kiro-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 88 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00058 | $0.03409 |
| Opus 5 | $0.00029 | $0.01705 |
| Sonnet 5 | $0.00012 | $0.00682 |
| Haiku 4.5 | $0.00006 | $0.00341 |
Grade A, and why
kiro-capture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kiro-capture
Capture kiro-cli HTTPS traffic with mitmdump and generate analysis reports.
Phase Detection
On invocation, find the latest session under /tmp/kiro-capture/:
LATEST=$(ls -dt /tmp/kiro-capture/*/ 2>/dev/null | head -1)
if [ -n "$LATEST" ] && [ -f "${LATEST}state.json" ]; then
cat "${LATEST}state.json"
fi
Decision logic:
state.jsonexists with"status": "capturing":- Check PID with
kill -0 <pid> - PID alive → ask user: "Capture in progress. Stop and analyze?" If yes → Phase 2
- PID dead → tell user "mitmdump already stopped. Analyzing log." → Phase 2
- Check PID with
state.jsonexists with"status": "completed"or"status": "analyzing"→ ask user: "Previous capture is done. Start a new capture?"- No
state.jsonor empty directory → Phase 1
Phase 1: Setup
Step 1 — Check prerequisites
which mitmdump
If not found:
brew install mitmproxy
Check CA certificate:
ls ~/.mitmproxy/mitmproxy-ca-cert.pem
If missing, run mitmdump once to generate it:
mitmdump --set flow_detail=0 &
MITM_PID=$!
sleep 2
kill $MITM_PID 2>/dev/null
wait $MITM_PID 2>/dev/null
Step 2 — Check port availability
lsof -i :8080 -t 2>/dev/null
If port 8080 is in use, try 8081, 8082, ... until a free port is found.
Step 3 — Create session directory
TIMESTAMP=$(date +%Y%m%d_%H%M%S)
SESSION_DIR="/tmp/kiro-capture/${TIMESTAMP}"
mkdir -p "$SESSION_DIR"
Step 4 — Start mitmdump
mitmdump -p $PORT --set flow_detail=3 >"${SESSION_DIR}/raw.log" 2>&1 &
MITM_PID=$!
sleep 1
kill -0 $MITM_PID 2>/dev/null && echo "OK" || echo "FAILED"
Step 5 — Save state.json
Write to ${SESSION_DIR}/state.json:
{
"status": "capturing",
"pid": <MITM_PID>,
"port": <PORT>,
"session_dir": "<SESSION_DIR>",
"started_at": "<ISO8601>"
}
Step 6 — Output kiro-cli launch command
Tell the user:
"mitmdump is running on port {PORT}. Run the following command in a separate terminal to start kiro-cli through the proxy:
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.
- 9d ago First seen · 418 lines · 58 tokens per session scan A a09402ee73c4
kiro-capture is a skill published in the GitHub repository d-kuro/kirocc (57 stars, last pushed 5d ago), licensed Apache-2.0. It adds 58 tokens to every session and 3,409 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
ha-logs
A read-only troubleshooting skill for querying Hope Agent’s local SQLite databases, which store logs, conversations, and background-job status.
ai-discover
Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.