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 agentmods add skills/codemie-ai/codemie-code/report-issuenpx skills add codemie-ai/codemie-code --skill report-issuegit clone --depth 1 https://github.com/codemie-ai/codemie-codeWhat 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 | $0.00187 | $0.02262 |
| Opus 5 | $0.00093 | $0.01131 |
| Sonnet 5 | $0.00037 | $0.00452 |
| Haiku 4.5 | $0.00019 | $0.00226 |
Grade B, and why
report-issue scanned grade B 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 2d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
> - **Linux (apt)**: `sudo apt install gh` How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Issue to CodeMie Code
Help the user file a well-structured bug report or feature request to codemie-ai/codemie-code on GitHub.
The goal is to create a rich issue that gives maintainers everything they need to triage and reproduce the problem — without requiring the user to manually gather technical details.
Step 1: Pre-flight and Diagnostic Collection
1a. Check gh CLI first — do this before anything else
if ! command -v gh &>/dev/null; then
echo "GH_NOT_INSTALLED"
else
gh auth status 2>&1 || echo "GH_NOT_AUTHENTICATED"
fi
If GH_NOT_INSTALLED: Stop immediately and tell the user:
"
gh(GitHub CLI) is not installed. It is required to create issues from the terminal.Install it with one of:
- macOS:
brew install gh- Linux (apt):
sudo apt install gh- Linux (dnf):
sudo dnf install gh- Windows:
winget install --id GitHub.cli- Or download from: https://cli.github.com
After installing, run
gh auth loginto connect your GitHub account, then try this skill again."
If GH_NOT_AUTHENTICATED: Stop and tell the user:
"
ghis installed but not authenticated. Rungh auth loginto connect to your GitHub account, then try again."
Do not proceed past this point until gh is installed and authenticated.
1b. Gather diagnostic context
Run the following and capture results. Don't display raw output yet.
# OS + platform
uname -srm 2>/dev/null || echo "unknown"
# Node.js version
node --version 2>/dev/null || echo "not found"
# npm version
npm --version 2>/dev/null || echo "not found"
# CodeMie CLI version
codemie --version 2>/dev/null || echo "not found"
# Installed agents and versions
codemie list --installed 2>/dev/null || echo "unavailable"
# Full doctor output (profile, provider, dependency health, agent versions)
codemie doctor 2>/dev/null || echo "unavailable"
# Shell + terminal environment
echo "Shell: $SHELL"
echo "Terminal: ${TERM_PROGRAM:-unknown}"
# Extract ERROR and WARN lines from the two most recent log files.
# Log format: [TIMESTAMP] [LEVEL] [agent] [session-id] [profile] [component] message
# Files: ~/.codemie/logs/debug-YYYY-MM-DD.log (one per day, can be several MB)
LOG_DIR="$HOME/.codemie/logs"
RECENT_LOGS=$(ls -t "$LOG_DIR"/debug-*.log 2>/dev/null | head -2)
if [ -n "$RECENT_LOGS" ]; then
echo "=== ERROR and WARN entries from recent logs ==="
# Print filename headers and filter by level; limit to last 100 matches to keep size reasonable
for f in $RECENT_LOGS; do
echo "--- $f ---"
grep -E '\[(ERROR|WARN)\]' "$f" | tail -50
done
echo "=== Full log files ==="
for f in $RECENT_LOGS; do
echo "$f"
done
else
echo "No debug logs found"
fi
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.
- 2d ago First seen · 290 lines · 187 tokens per session scan B 721a30f83d2c
report-issue is a skill published in the GitHub repository codemie-ai/codemie-code (276 stars, last pushed 3d ago), licensed Apache-2.0. It adds 187 tokens to every session and 2,262 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 1 finding (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
babysit
Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…
teamharness-task-delegation
Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.
github-workflow
Use GitHub workflow tools to read work status, draft reports, summarize follow-ups, and execute only approved issue mutations.
flow-next-tracker-sync
Project a flow-next spec to a tracker issue (Linear, GitHub, GitLab, Jira) and reconcile two-way. Use when asked to sync to a tracker. NOT plan-sync.
gsd-executor
Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management. Spawned by execute-phase orchestrator or execute-plan command.
dot-ai-prd-create
Create documentation-first PRDs that guide development through user-facing content.