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 Jamie-BitFlight/claude_skills --skill bash-52-featuresgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/bash-52-features)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/bash-52-features"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/bash-52-features/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/jamie-bitflight/claude_skills/bash-52-features"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/bash-52-features.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.01501 |
| Opus 5.5 | $0.00023 | $0.00600 |
| Sonnet 5.5 | $0.00012 | $0.00300 |
| Haiku 4.5 | $0.00006 | $0.00150 |
Grade A, and why
bash-52-features scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bash 5.2 Features and Improvements
Released in September 2022, Bash 5.2 brought enhancements to variable handling, readline integration, array support, and numerous bug fixes.
Variable Handling Enhancements
Improved Readonly and Unset Variable Behavior
Better error messages and more consistent behavior:
# More informative error messages for readonly variables
readonly CONFIG_PATH="/etc/app/config"
# Attempting to modify generates clearer error
CONFIG_PATH="/tmp/config" # bash: CONFIG_PATH: readonly variable
# Better handling of unset variables with set -u
set -u
# Checking before use is now more reliable
if [[ -n "${OPTIONAL_VAR:-}" ]]; then
echo "Variable is set: ${OPTIONAL_VAR}"
else
echo "Variable is not set"
fi
# Practical example: Configuration validation
validate_config() {
local -a required_vars=("DATABASE_URL" "API_KEY" "LOG_DIR")
local var
for var in "${required_vars[@]}"; do
if [[ -z "${!var:-}" ]]; then
printf 'Error: Required variable %s is not set\n' "${var}" >&2
return 1
fi
done
echo "All required configuration variables are set"
}
export DATABASE_URL="postgres://localhost/db"
export API_KEY="secret123"
export LOG_DIR="/var/log/app"
validate_config
Nameref Improvements
Enhanced reference variable handling.
Readline 8.2 Integration
Significant improvements to command-line editing:
Enhanced Completion and History
# Better completion behavior in ~/.inputrc
# Skip completions for invisible characters
set skip-completed-text on
# Enhanced history search
# Cycle through history with prefix matching
bind '"\e[A": history-search-backward' # Up arrow
bind '"\e[B": history-search-forward' # Down arrow
# Improved completion coloring
set colored-stats on
set colored-completion-prefix on
# Better handling of long completions
set completion-display-width 0 # Use full terminal width
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.
- 2mo ago First seen · 224 lines · 58 tokens per session scan A 73841e9c6088
bash-52-features is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (67 stars, last pushed 19d ago), licensed MIT. It adds 58 tokens to every session and 1,501 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
bash-52-features compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bash-52-featuresJamie-BitFlight/claude_skills | Skill | 67 | 19d ago | MIT | A | 58 | Claude Code |
| erlang-otp-behaviorsbenchflow-ai/skillsbench | Skill | 1.9k | 4d ago | Apache-2.0 | A | 52 | Claude Code, Codex |
| omh-rustrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 74 | Claude Code, Codex |
| axiom-concurrencyCharlesWiltgen/Axiom | Skill | 1.3k | 2d ago | MIT | A | 49 | Claude Code |
| tddcodewithmukesh/dotnet-claude-kit | Skill | 807 | 3d ago | MIT | A | 81 | Claude Code |
| splitting-oversized-modulesPostHog/posthog | Skill | 41k | today | none | A | 197 | Claude Code, Codex |
| precisemicroprediction/precise | Skill | 338 | 6d ago | MIT | A | 76 | Claude Code, Codex |