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 humanerd-drew/opencode-drewgent --skill shell-init-side-effect-gatinggit clone --depth 1 https://github.com/humanerd-drew/opencode-drewgentWrote 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/humanerd-drew/opencode-drewgent/shell-init-side-effect-gating)<a href="https://agentmods.dev/skills/humanerd-drew/opencode-drewgent/shell-init-side-effect-gating"><img src="https://agentmods.dev/badge/skills/humanerd-drew/opencode-drewgent/shell-init-side-effect-gating.svg" alt="Measured on agentmods" 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 | $0.00121 | $0.01349 |
| Opus 5 | $0.00060 | $0.00674 |
| Sonnet 5 | $0.00024 | $0.00270 |
| Haiku 4.5 | $0.00012 | $0.00135 |
Grade A, and why
shell-init-side-effect-gating scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run( How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Shell Init Side-Effect Gating
When to load
Trigger when:
- User asks to add or modify
.zshrc/.zshenv/.zprofile/.zlogin/.bashrc/.bash_profile - User shows a
[N] PIDjob notification or other unexpected background process on shell login - User asks to silence a
[N] PIDnotification (audit first, don't just slap&!on it) - Reviewing existing shell init for cleanup or refactor
Steps
-
Find all
&in shell init:grep -nE '&\s*$' ~/.zshenv ~/.zshrc ~/.zprofile ~/.zlogin 2>/dev/null -
For each backgrounded process, identify its consumer (RPROMPT, prompt segment, alias, key binding, function called from elsewhere).
-
Check the consumer's gate — is it conditional on a marker file, TTY,
$DISPLAY,uname, etc.? -
Compare gates:
- Consumer gated, side effect not → leak
- Both gated the same way → fine
- Both ungated → fine
- Side effect gated, consumer not → consumer might be missing optimization
-
Decide on fix (in this priority order):
- A. Move side effect to consumer's entry point (e.g., wrapper function) — preferred
- B. Apply same gate to side effect — if gate is static at source time
- C. Silence with
&!— only if leak is acceptable and noise is the only complaint - D. Make consumer unconditional — only if re-evaluating design intent confirms broad usefulness
-
Verify:
zsh -c 'source ~/.{{AGENT_NAME_LOWER}}/.zshrc_aliases; sleep 0.3; jobs -l' 2>&1Should report no jobs (or only the ones you intended).
-
Document the change in
P4-cortex/growth/patterns/shell-init-side-effect-gating.md.
Anti-patterns
- ❌ Adding
&"for performance" without checking the consumer's gate - ❌ Slapping
&!on every&to silence notifications - ❌ Treating
[N] PIDas "noise to silence" — it's a symptom pointing at a real issue - ❌ Moving the side effect to a wrapper without checking that the wrapper actually gates the consumer
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.
- 4d ago First seen · 116 lines · 121 tokens per session scan A 890810a0b630
shell-init-side-effect-gating is a skill published in the GitHub repository humanerd-drew/opencode-drewgent (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,349 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.