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.svg" alt="Measured on agentmods" 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 | $0.01341 |
| Opus 5 | $0.00013 | $0.00671 |
| Sonnet 5 | $0.00005 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
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 8d 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 — 97 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.
- 8d 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 5d ago), licensed MIT. It adds 25 tokens to every session and 1,341 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…
cherry-electron-dev
Develop, fix, and profile Cherry Studio in a tracked Electron instance. Use for everyday implementation, UI and interaction work, bug fixing, runtime debugging, DevTools inspection, lag or jank investigation, CPU and memory monitoring, leak checks, and startup-performance analysis; reuse a verified workspace instance…
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-studio-feedback
A guide for handling Cherry Studio bug reports, interface problems, user-experience issues, and feature suggestions.
memstack-development-performance-audit
Use this skill when the user says 'performance audit', 'why is it slow', 'optimize performance', 'page speed', 'Core Web Vitals', 'lighthouse', 'load time', or needs to diagnose and fix frontend or backend performance issues. Do NOT use for code reviews or security audits.
debug
Use this skill to locate a runtime bug. Add targeted instrumentation, collect reproduction evidence, and confirm the root cause before changing code.