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 pjt222/agent-almanac --skill decode-minified-js-gatesgit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/decode-minified-js-gates)<a href="https://agentmods.dev/skills/pjt222/agent-almanac/decode-minified-js-gates"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/decode-minified-js-gates/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/pjt222/agent-almanac/decode-minified-js-gates"><img src="https://agentmods.dev/badge/skills/pjt222/agent-almanac/decode-minified-js-gates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Data Exfiltration · line 53 Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.Fix: Remove any code that sends prompts, responses, or session data externally. Preserve user privacy; never exfiltrate conversation content.
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 | $0.00138 | $0.03620 |
| Opus 5 | $0.00069 | $0.01810 |
| Sonnet 5 | $0.00028 | $0.00724 |
| Haiku 4.5 | $0.00014 | $0.00362 |
Grade A, and why
decode-minified-js-gates 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 7d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Decode Minified JS Gates
Read the call-site context around a flag string in a minified JavaScript bundle and produce a gate-mechanics record: which reader variant, what default, what conjunction, what role. Where probe-feature-flag-state answers "is this gate on or off?", this skill answers the prerequisite question — "what does this gate actually do?"
When to Use
- A flag surfaced by
sweep-flag-namespacecannot be classified from its name alone. - The binary uses more than one gate-reader function and you need to know which one a flag invokes.
- A gate's "default" appears non-boolean (
{},null, a numeric literal) and you need to decode the actual reader variant. - You suspect a kill-switch (inverted gate) but cannot confirm from the flag name.
- A predicate combines multiple gates with
&&and you need to enumerate the co-gates before probing any of them.
Inputs
- Required: a minified JavaScript bundle file (
.js,.mjs,.bun). - Required: a target flag string to decode, in literal form.
- Optional: a list of known reader function names from a prior decode pass — speeds Step 2.
- Optional: a context-window size override; default is 300 chars before, 200 chars after the flag occurrence.
Procedure
Step 1: Extract the Context Window
Locate the flag string and capture an asymmetric window around each occurrence. The pre-context (before the flag) is where the reader function name lives; the post-context (after) is where the default value and conjunction live.
BUNDLE=/path/to/cli/bundle.js
FLAG=acme_widget_v3 # synthetic placeholder
PRE=300
POST=200
# All byte offsets where the flag string occurs
grep -boE "\"${FLAG}\"" "$BUNDLE" | cut -d: -f1 > /tmp/decode-offsets.txt
wc -l /tmp/decode-offsets.txt
# Capture an asymmetric window per occurrence
while read -r offset; do
start=$((offset - PRE))
[ "$start" -lt 0 ] && start=0
length=$((PRE + POST))
echo "=== offset $offset ==="
dd if="$BUNDLE" bs=1 skip="$start" count="$length" 2>/dev/null
echo
done < /tmp/decode-offsets.txt > /tmp/decode-windows.txt
less /tmp/decode-windows.txt
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.
- 7d ago First seen · 221 lines · 138 tokens per session scan A 304b4b62e1be
decode-minified-js-gates is a skill published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed today), licensed MIT. It adds 138 tokens to every session and 3,620 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
triage-issue
Verify an issue, persisted audit finding, or unresolved review finding against current code, classify it, and write only the contracted forge/ledger outcome. Supports independent batches and an immediate-fix review-finding route. Triggers: "triage-issue", "triage issue N", "triage this finding", "is this trigger met".
loop-react-doctor
Iterative React-health loop: inventory every React app in the repo, baseline with the latest react-doctor (pinned for the rest of the run), fix one root cause per iteration, and re-verify until every app scores 100/100 or every remaining finding has a user-approved written justification. Never silences findings with…
dev-performance-diagnosis
Use for diagnosing slow code, APIs, queries, memory growth, frontend load, build regressions, resource bottlenecks, and scalability limits.
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
airflow-plugins
Builds Airflow 3.1+ plugins that embed FastAPI apps, custom UI pages, React components, middleware, macros, and operator links directly into the Airflow UI. Use when building anything custom inside Airflow 3.1+ that involves Python and a browser-facing interface - creating an Airflow plugin, adding a custom UI page or…
qwen-coder
Provides Qwen Coder CLI delegation workflows for coding tasks using Qwen2.5-Coder and QwQ models, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Qwen for tasks such as code generation, refactoring, debugging, or architectural analysis. Triggers…