Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
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.
npx skills add kirodotdev/KiroCrew --skill gateway-restartgit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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/kirodotdev/kirocrew/gateway-restart)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/gateway-restart"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/gateway-restart.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 12 findings, up to high
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 →
- high Rogue Agent · line 146 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 182 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 146 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- high Rogue Agent · line 182 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 134 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 26 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.
- medium Rogue Agent · line 113 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.
- medium Rogue Agent · line 26 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.
- medium Rogue Agent · line 113 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.
- medium Prompt Injection · line 134 Subtle instructions detected that may alter agent decision-making or introduce hidden biases.Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
- medium Privilege Escalation · line 138 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Rogue Agent · line 139 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 | $0.00052 | $0.03978 |
| Opus 5 | $0.00026 | $0.01989 |
| Sonnet 5 | $0.00010 | $0.00796 |
| Haiku 4.5 | $0.00005 | $0.00398 |
Grade C, and why
gateway-restart scanned grade C with 2 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 today.
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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
**Never tell the user the restart succeeded without checking.** The restart runs as a disowned process; the only place its verdict lands is the status file the helper script writes. When the resume cron fires, take the a Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
3. **Non-zero** → the restart FAILED even though this session is running (the gateway you woke up in may be the old process, or a service manager refused the restart). Read the tail of the attempt's own log — `<status fi How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gateway Restart
Overview
Gracefully restart the KiroCrew gateway from within a running agent session. The challenge: kirocrew restart is blocked by kiro-cli's security filter, and killing the gateway kills the current session. This skill teaches the agent to schedule the restart externally and resume the conversation afterward.
Core Concepts
The Problem
The agent cannot directly run kirocrew restart — kiro-cli blocks it. Even if it could, the restart would kill the agent mid-response. The solution is a two-phase approach: schedule resume jobs, then trigger the restart via a mechanism that runs outside the agent session.
Restart Mechanism
The agent cannot run kirocrew restart directly — kiro-cli's security filter blocks it at the shell command level (regex match on the command string). Platform-specific scripts handle this indirectly:
Linux / macOS:
nohup /path/to/skills/gateway-restart/do-restart.sh >/dev/null 2>&1 & disown
The script sleeps 10 seconds (giving the session time to respond), then invokes the restart. Because it's a detached process reparented to PID 1, it survives the gateway's death and executes reliably.
Both scripts record the outcome instead of discarding it: the restart's exit status is written to a status file under <crew home>/logs/ and its output goes to a log correlated with that attempt — <status file>.log when an attempt-specific status file is passed, the shared logs/restart.log for a lone unscheduled run (crew home is $KIROCREW_HOME, default ~/.kiro/crew; both scripts derive their paths from it, so never pass hardcoded %USERPROFILE% paths). The status file is attempt-specific when the scheduler passes one — KIROCREW_RESTART_STATUS_FILE (Linux/macOS) or -StatusFile (Windows), see step 3 — so overlapping restart attempts cannot overwrite each other's verdict or quote each other's diagnostics; without it the shared default logs/restart-status is used. The file is removed when the attempt starts, so while it is absent the attempt is pending; once present it names that attempt's exit status. The CLI restart verb itself verifies the replacement gateway is serving and exits non-zero when it is not — the status file is how that verdict reaches the resumed session (see "Verify the outcome" below).
What ships with it
2 files 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.
- today Changed · +7 lines 6c7f13ff977a
- 5d ago Changed · +29 lines scan A → C 386f1a2aa4d8
- 8d ago First seen · 161 lines · 52 tokens per session scan A c6ded2290a17
gateway-restart is a skill published in the GitHub repository kirodotdev/KiroCrew (3,687 stars, last pushed today), licensed Apache-2.0. It adds 52 tokens to every session and 3,978 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (subtle steering, asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
executive-financial-briefing
Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also…
multi-quarter-trend-analysis
Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.
persistent-notes
Save notes locally to /mnt/workspace/notes.json file. Use when user wants to "save a note" or "remember something".
benefits-advisor
Explain an Acme employee benefit, including eligibility, employee cost, coverage, and key details.