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/phobologic/claude_code_helpers/load-shared-rulenpx skills add phobologic/claude_code_helpers --skill load-shared-rulegit clone --depth 1 https://github.com/phobologic/claude_code_helpersWhat 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 | $0.00086 | $0.00797 |
| Opus 5 | $0.00043 | $0.00398 |
| Sonnet 5 | $0.00017 | $0.00159 |
| Haiku 4.5 | $0.00009 | $0.00080 |
Grade A, and why
load-shared-rule scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
load-shared-rule
Wires a single opt-in rule from ~/.claude/optional_rules/ into the
current project's .claude/rules/ directory as a symlink. The rule
is auto-loaded by Claude Code at the start of the next session.
Argument
One positional argument: the rule name without extension (e.g.
skeletons to load ~/.claude/optional_rules/skeletons.md).
If the user did not specify a rule name, ask them which rule to load and list available rules with:
ls ~/.claude/optional_rules/
Procedure
Run the following as a single bash invocation, substituting the rule
name for RULE. Do not split it into multiple Bash calls — the
checks chain together and short-circuit on first failure.
RULE=<name>; \
SRC="$HOME/.claude/optional_rules/$RULE.md"; \
if [[ ! -e "$SRC" ]]; then \
echo "error: rule '$RULE' not found at $SRC"; \
echo "available rules:"; ls "$HOME/.claude/optional_rules/"; \
exit 1; \
fi; \
ROOT="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"; \
if [[ "$ROOT" == "$HOME" || "$ROOT" == "$HOME/.claude" ]]; then \
echo "error: refusing to install into $ROOT — run from inside a project repo"; \
exit 1; \
fi; \
DST="$ROOT/.claude/rules/$RULE.md"; \
mkdir -p "$ROOT/.claude/rules"; \
if [[ -L "$DST" ]]; then \
CUR="$(readlink "$DST")"; \
if [[ "$CUR" == "$SRC" ]]; then \
echo "already linked: $DST -> $SRC"; \
exit 0; \
else \
echo "conflict: $DST is a symlink to $CUR (expected $SRC) — not overwriting"; \
exit 1; \
fi; \
elif [[ -e "$DST" ]]; then \
echo "conflict: $DST exists as a regular file — not overwriting"; \
exit 1; \
fi; \
ln -s "$SRC" "$DST"; \
echo "linked: $DST -> $SRC"; \
echo "loaded rule: $RULE"; \
echo "start a fresh Claude Code session in $ROOT to pick up the rule"
Reporting
After the command runs, relay its outcome to the user in one short line. If it printed "already linked", say so and stop. If it errored on conflict or missing rule, surface the error verbatim. On success, remind the user to start a fresh session for the rule to take effect.
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 · 81 lines · 86 tokens per session scan A 7e8d6944637b
load-shared-rule is a skill published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 86 tokens to every session and 797 once invoked, about $0.0004 per session on Opus 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 2026-08-31.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.