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 gosha70/code-copilot-team --skill safetygit clone --depth 1 https://github.com/gosha70/code-copilot-teamWrote 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/gosha70/code-copilot-team/safety)<a href="https://agentmods.dev/skills/gosha70/code-copilot-team/safety"><img src="https://agentmods.dev/badge/skills/gosha70/code-copilot-team/safety/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/gosha70/code-copilot-team/safety"><img src="https://agentmods.dev/badge/skills/gosha70/code-copilot-team/safety.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 | $0.00030 | $0.00657 |
| Opus 5.5 | $0.00012 | $0.00263 |
| Sonnet 5.5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade C, and why
safety scanned grade C 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 1mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Any destructive command: rm -rf, DROP TABLE, TRUNCATE, git reset --hard, git push --force. How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Safety Rules
Non-negotiable safety constraints for all sessions.
Confirmation Required Before
- Any destructive command: rm -rf, DROP TABLE, TRUNCATE, git reset --hard, git push --force.
- Any deployment or publish action.
- Any command that modifies production data.
- Any command with side effects outside the working directory.
Blocked Operations — Stop, Don't Improvise
When the normal path for an operation is blocked (lock files, permission errors, sandbox restrictions), the correct response is to stop and explain the blockage to the user — not to improvise a workaround using low-level flags or environment variables.
Specific prohibitions:
- Never set
GIT_INDEX_FILE,GIT_DIR, or other git environment variables to route around lock files or index problems. - Never use
--no-verify,--no-gpg-sign, or similar flags to bypass pre-commit hooks or signing unless the user explicitly requests it. - Never bypass sandbox restrictions, file permission checks, or process locks by manipulating environment variables or creating alternate state files.
Why: A real incident demonstrated this failure mode — using GIT_INDEX_FILE to bypass .git/index.lock created a commit with an empty tree that appeared to delete every file in the repository. The copilot pattern-matched "bypass the lock" without reasoning about the consequence (an empty alternate index). The correct move was to explain that the lock file was blocking the commit and ask the user to remove it.
Published State Is Verified, Not Held
A PreToolUse hook sees only the agent's own commands; an external
publisher can push any commit that exists locally. "Held locally" is
advisory, not a boundary.
- Never claim a commit can be kept unpublished.
- Report push status from
git ls-remote/reflog, not your own log. - Bind review/merge/closure to an exact SHA; re-read state first.
- Prefer a follow-up commit to an amend on a watched branch.
- Keep every commit review-ready.
Evidence, and the guard not adopted: #291.
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.
- 1mo ago Changed · +14 lines 237e0c7ca1bd
- 1mo ago First seen · 52 lines · 30 tokens per session scan C 0ebd3a1031dd
safety is a skill published in the GitHub repository gosha70/code-copilot-team (7 stars, last pushed 17d ago), licensed MIT. It adds 30 tokens to every session and 657 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
fleet
Fan out a fleet of independent agent-deck child sessions from inside a session and check their progress non-blockingly. Use when the user wants to "launch several/N sessions", "fan out", "run agents in parallel", "spin up a fleet", "kick off background agents", or "check progress from the main session" without…
watcher-creator
Guide for creating agent-deck watchers conversationally. This skill should be used when users want to set up a new watcher (webhook, ntfy, github, slack, gmail) to route events to a conductor. It walks the user through selecting an adapter type, gathering required settings, generating watcher.toml and clients.json…
agent-deck
Helper scripts live in this skill's scripts/ folder. Resolve them from the base directory shown when the skill loaded, not from the user's project.
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
x-spec
A system-planning guide that turns a vague idea into a set of linked design documents. It defines goals, modules, interfaces, data, workflows, and ways to check the result.
x-audit-arch
A project-wide architecture review skill that checks whether code is placed in the right modules and whether important definitions have one reliable source.