tool-guide

A guide for choosing the right CloudLedger tool or task skill for an AWS question. CloudLedger is a service that provides information about scanned AWS accounts.

In plain words
What is it for?
Routing questions about account inventory, security assessments, costs, security-group audits, and possible attack paths to the corresponding CloudLedger tools or skills.
Why use it?
It helps avoid using a tool that returns the wrong kind of data, such as using security findings to answer a simple inventory question.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cognisn/cloudledger/tool-guide
Any agent
npx skills add Cognisn/cloudledger --skill tool-guide
Clone the repo
git clone --depth 1 https://github.com/Cognisn/cloudledger

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,084 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00075 $0.01084
Opus 5 $0.00037 $0.00542
Sonnet 5 $0.00015 $0.00217
Haiku 4.5 $0.00007 $0.00108

Measured yesterday against content hash 570f011d9a84, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tool-guide 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 yesterday.

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.

skills/tool-guide/SKILL.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tool guide

The CloudLedger server exposes ~50 tools. This guide routes a question to the right tool or specialised skill so you do not answer with the wrong data. get_security_check_catalogue and the server's tool list are authoritative at runtime; this guide is the map.

First: is there a task skill for this?

Prefer the specialised skill when the request matches one — it encodes the full workflow and the correct tool sequence:

The user wants… Use skill
A scored security assessment / report security-assessment
What services/resources exist and how many account-inventory
Cost breakdown, trends, or forecast cost-analysis
A full security group audit and implications security-groups-review
Attack paths / MITRE ATT&CK / "how could this be compromised" attack-path-analysis

If the request is a single focused lookup, go straight to the tool below.

The routing rules that prevent wrong answers

  1. Inventory / "how many X" → summary tools, never the findings tools. Use get_scan_summary (resource_counts) and the per-service summaries. get_security_assessment_data and analyze_service_exposure return findings only and will undercount resources badly.
  2. A security score is never returned by the server. The tools return findings with advisory severities; scoring is done by the security-assessment skill's rubric.
  3. "None found" is not "unknown". A 0 count or a not_applicable check means the account has none of that resource — state it as absent, not a gap.
  4. Organizations cost questions → get_organizations_cost_breakdown, not get_total_cost alone, or the payer account looks like it dominates.
  5. Default to the latest scan unless the user names a scan_id; use list_scans (accepts account_number) to find a specific account's scan.

Tools by question

Scans and inventory

  • list_scans, get_scan_summary — which scans exist; per-scan resource counts.
  • get_ec2_summary_by_account, get_lambda_summary, get_workspaces_summary — per-service counts and detail.
  • compare_scans, get_ec2_changes, get_route53_changes — change over time.

Read the full file on GitHub · 90 lines

Changes

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.

  1. yesterday First seen · 90 lines · 0 tokens per session scan A 570f011d9a84

Subscribe to this mod's changes

tool-guide is a skill published in the GitHub repository Cognisn/cloudledger (0 stars, last pushed 13d ago), licensed MIT. It adds 75 tokens to every session and 1,084 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.