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/infohata/mind-vault/shellnpx skills add infohata/mind-vault --skill shellgit clone --depth 1 https://github.com/infohata/mind-vaultWhat 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 | $0.00063 | $0.03688 |
| Opus 5 | $0.00032 | $0.01844 |
| Sonnet 5 | $0.00013 | $0.00738 |
| Haiku 4.5 | $0.00006 | $0.00369 |
Grade D, and why
shell scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- [references/INTERACTIVE_SUDO_LOGIN_SHELL.md](references/INTERACTIVE_SUDO_LOGIN_SHELL.md) — the *interactive* sibling of `PRIVILEGE_DROP_PORTABILITY.md`: `sudo -iu <user>` / `sudo -i` / `su -` opens a login shell that b Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
`trap 'rm -rf -- "$tmp"' EXIT HUP INT TERM` registered immediately after How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
shell
The vault's base shell-language layer — what python is to the framework
skills, shell is to ops work: language-general recipes beneath the
deployment skill and the devops persona. Two tiers live here:
- Language mechanics (patterns 1–3 + the non-negotiables): true of any bash script — deploy tooling, installers, cron jobs, CI steps, maintenance scripts.
- Live-host ops machinery (patterns 4–7): scripts that mutate live systems — mode surfaces, operator gates, SSH sweep hygiene, safe config edits, evidence gates.
deployment owns the Docker-Compose deploy lifecycle and machine provisioning;
its references point down into this layer for the language-general mechanics
rather than restating them. New shell-general patterns land here, not under
deployment by gravity.
When to use
TRIGGER when: writing or reviewing any bash/sh script — ops/maintenance/rollout tooling, cron jobs, CI steps, entrypoints; user asks to "make this script safe to re-run"; adding or auditing DRY-RUN / --apply / --verify mode surfaces; sweeping a host fleet over SSH; editing system config files (PAM stack, nsswitch.conf, login-path or firewall config) from a script; designing precondition checklists for operator tooling.
SKIP when: the script is a Docker-Compose deploy / backup / rollback (→ deployment owns that lifecycle) or a machine-provisioning installer (→ deployment's SHELL_INSTALLERS.md leads and reaches down into this layer); one-shot commands a human types interactively.
Language mechanics
1. Strict mode and its holes
Fires when authoring any script. set -euo pipefail (+ shopt -s inherit_errexit on bash ≥4.4 — without it multi-step command substitutions
sail past a failing first step) is the house prologue AND a known-leaky
tripwire: pipeline-in-assignment aborts before your friendly
error, head -N SIGPIPE races, informative non-zero rcs (diff, grep),
local var=$(cmd) masking failure (SC2155), condition contexts disabling
errexit transitively (if f; then turns -e off inside all of f), unguarded
cd (SC2164), (( i++ )) at zero. Explicit rc handling at every destructive
step, as if -e were absent; never retrofit -e onto a working script.
Full catalog + the honest judgment-call stance:
references/STRICT_MODE_HAZARDS.md.
What ships with it
11 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.
- references/CLEANUP_TRAPS_AND_LOCKING.md 3.4 KB
- references/EVIDENCE_SCRIPTS_AND_FALSE_CLEANS.md 28 KB
- references/INTERACTIVE_SUDO_LOGIN_SHELL.md 3.4 KB
- references/INTERMITTENT_FAULT_GATING.md 4.7 KB
- references/MAINTENANCE_SCRIPT_CONTRACT.md 30 KB
- references/PRIVILEGE_DROP_PORTABILITY.md 3.8 KB
- references/QUOTING_AND_INPUT_HYGIENE.md 4.9 KB
- references/SAFE_CONFIG_EDITS.md 20 KB
- references/SSH_FLEET_PATTERNS.md 5.0 KB
- references/STRICT_MODE_HAZARDS.md 13 KB
- references/SUDOERS_WHITELIST_FENCES.md 9.9 KB
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 · 171 lines · 63 tokens per session scan D dcee99cfd651
shell is a skill published in the GitHub repository infohata/mind-vault (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 63 tokens to every session and 3,688 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…