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 kangig94/coral --skill analyzegit clone --depth 1 https://github.com/kangig94/coralWrote 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/kangig94/coral/analyze)<a href="https://agentmods.dev/skills/kangig94/coral/analyze"><img src="https://agentmods.dev/badge/skills/kangig94/coral/analyze/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/kangig94/coral/analyze"><img src="https://agentmods.dev/badge/skills/kangig94/coral/analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Prompt Injection · line 71 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00025 | $0.01387 |
| Opus 5.5 | $0.00010 | $0.00555 |
| Sonnet 5.5 | $0.00005 | $0.00277 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
analyze 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 today.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Analysis & Investigation
Strip the --delegate flag before passing the prompt to the execution path.
</Argument_Routing>
Phase 1 — Create Analysis File
Write CORAL_PROJECT/analysis/{YYYY-MM-DD}-{topic}.md with header:
# Analysis: {topic}
Date: {YYYY-MM-DD}
Question: {user's original request}
- Topic: 2-4 word kebab-case (e.g.,
auth-flow-gaps,ci-pipeline-root-cause) - Collision: same date + topic → append
-2,-3
Phase 2 — Investigation Steps
For each step in the table below, in order:
- Evaluate — check "Needed when" against the user's request AND prior findings. Skip if unneeded.
- Scope — determine target files/modules. Never run unscoped. If a step discovers new facets, carry them into subsequent step evaluation.
- Execute — run via active mode (see Mode below).
- Post-process — apply quality gates:
- Verify CRITICAL/HIGH file:line references (Read cited location, drop incorrect)
- Drop speculative findings without code evidence. Findings about unchanged code: downgrade and move to
### Peripheral Findings - Tag provenance (code trace / test behavior / git history / inference / assumption). Assumption-only → downgrade one level
- Record finding flow: "N initial → M after gates → K verified [code: X, inference: Y, assumption: Z]"
- Append — write under the step's output section heading.
Wait for each step's result before evaluating the next. At least one step must run.
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.
- today Changed 9574deab35d8
- 5d ago Changed e9c350d92eca
- 15d ago Changed d1a7cb1e63cc
- 29d ago Changed · -1 lines 9939f0197a82
- 1mo ago First seen · 97 lines · 25 tokens per session scan A bc44483f8b9c
analyze is a skill published in the GitHub repository kangig94/coral (11 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,387 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-workflow-ddd
Domain-Driven Development workflow specialist using ANALYZE-PRESERVE-IMPROVE cycle for behavior-preserving code transformation. Use when refactoring legacy code or reducing technical debt safely.
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
cherry-assistant-guide
A guide for looking up Cherry Studio's product details and diagnosing problems such as connection failures, setup errors, and runtime issues.
cherry-electron-dev
Develop, fix, profile, and test PRs in a tracked Cherry Studio Electron instance. Use for implementation, UI and interaction work, runtime debugging, DevTools inspection, performance analysis, and interactive PR verification with a test report. Reuse a verified workspace instance and manage its lifetime according to…
cherry-studio-feedback
A guide for handling Cherry Studio bug reports, interface problems, user-experience issues, and feature suggestions.