Agent Cost Report

Each tab says whether it installs commit 35f2ec0, the one we checked, or the latest version.

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/thedotmack/claude-mem.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  git -C "$tmp" sparse-checkout set -- claude-mem-cursor/skills/agent-cost-report &&
  git -C "$tmp" checkout -q 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  mkdir -p .claude/skills &&
  mkdir .claude/skills/agent-cost-report &&
  cp -R "$tmp"/claude-mem-cursor/skills/agent-cost-report/. .claude/skills/agent-cost-report/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/thedotmack/claude-mem.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  git -C "$tmp" sparse-checkout set -- claude-mem-cursor/skills/agent-cost-report &&
  git -C "$tmp" checkout -q 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  out="$(mktemp -d)" &&
  cp -R "$tmp"/claude-mem-cursor/skills/agent-cost-report "$out"/agent-cost-report &&
  (cd "$out" && zip -qr - agent-cost-report) > agent-cost-report.zip &&
  rm -rf "$tmp" "$out"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/thedotmack/claude-mem.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  git -C "$tmp" sparse-checkout set -- claude-mem-cursor/skills/agent-cost-report &&
  git -C "$tmp" checkout -q 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/agent-cost-report &&
  cp -R "$tmp"/claude-mem-cursor/skills/agent-cost-report/. .agents/skills/agent-cost-report/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/thedotmack/claude-mem.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  git -C "$tmp" sparse-checkout set -- claude-mem-cursor/skills/agent-cost-report &&
  git -C "$tmp" checkout -q 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  mkdir -p .cursor/skills &&
  mkdir .cursor/skills/agent-cost-report &&
  cp -R "$tmp"/claude-mem-cursor/skills/agent-cost-report/. .cursor/skills/agent-cost-report/ &&
  rm -rf "$tmp"

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/thedotmack/claude-mem.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  git -C "$tmp" sparse-checkout set -- claude-mem-cursor/skills/agent-cost-report &&
  git -C "$tmp" checkout -q 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  mkdir -p .github/skills &&
  mkdir .github/skills/agent-cost-report &&
  cp -R "$tmp"/claude-mem-cursor/skills/agent-cost-report/. .github/skills/agent-cost-report/ &&
  rm -rf "$tmp"

gh skill install thedotmack/claude-mem claude-mem-cursor/skills/agent-cost-report/SKILL.md@35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 --agent github-copilot --scope project

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/thedotmack/claude-mem.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  git -C "$tmp" sparse-checkout set -- claude-mem-cursor/skills/agent-cost-report &&
  git -C "$tmp" checkout -q 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  mkdir -p .gemini/skills &&
  mkdir .gemini/skills/agent-cost-report &&
  cp -R "$tmp"/claude-mem-cursor/skills/agent-cost-report/. .gemini/skills/agent-cost-report/ &&
  rm -rf "$tmp"

gemini skills install https://github.com/thedotmack/claude-mem.git --path claude-mem-cursor/skills/agent-cost-report --scope workspace

tmp="$(mktemp -d)" &&
  git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/thedotmack/claude-mem.git "$tmp" &&
  git -C "$tmp" fetch -q --depth 1 origin 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  git -C "$tmp" sparse-checkout set -- claude-mem-cursor/skills/agent-cost-report &&
  git -C "$tmp" checkout -q 35f2ec0eb5b2b1e745564db4ce1ecec58eb331e7 &&
  mkdir -p .agents/skills &&
  mkdir .agents/skills/agent-cost-report &&
  cp -R "$tmp"/claude-mem-cursor/skills/agent-cost-report/. .agents/skills/agent-cost-report/ &&
  rm -rf "$tmp"

From the files and frontmatter at commit 35f2ec0. This is how much a skill can do, not whether it is risky.

What it can touch: Shell, network or credentials

• Runs shell commands

  Its instructions or files give the agent commands to run on your computer.

• Reaches the network

  It sends or fetches data over the internet, for example with curl, an HTTP library or a package install.

• Names web addresses

  It mentions outside web addresses the agent may visit. We list them but don't follow them.

• Bundles scripts

  The folder holds code files the agent may run.

  scripts/tests/_db.py · scripts/tests/_paths.py · scripts/tests/fixtures/make_report_fixtures.py and 15 more

• Pre-approves tools

  Its allowed-tools field lists tools the agent may use without asking you first, in agents that honour it.

  SKILL.md:9

• Touches credentials

  It reads, asks for or contains keys, tokens, passwords or similar secrets.

  scripts/tests/test_measure.py:60

Pattern check: 2 items to review · commit 35f2ec0 · 26 Oct 2026

• R38 · HighName copied from another skill

  SKILL.md:2 (opens in a new tab)

  name: Agent Cost Report

• R34 · HighBroad tools pre-approved in allowed-tools

  SKILL.md:9 (opens in a new tab)

  - Bash

We checked every text file in this skill, at commit 35f2ec0 on 26 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

• Agent Skills specFails

  The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

  • Error

    The name "Agent Cost Report" has uppercase letters and spaces. Names may use only a–z, 0–9 and single hyphens. N3

    Fix: Use name: agent-cost-report.

  • Error

    The name "Agent Cost Report" doesn't match its folder "agent-cost-report". The spec requires them to match. N4

    Fix: Set name: agent-cost-report, or rename the folder to agent-cost-report.

  • Warning

    allowed-tools is a list; the spec defines a space-separated string. gh skill publish rejects a list, though Claude Code accepts one. O5

    Fix: Write it on one line: allowed-tools: Bash Read Write AskUserQuestion mcp__plugin_claude-mem_mcp-search__search mcp__plugin_claude-mem_mcp-search__timeline mcp__plugin_claude-mem_mcp-search__get_observations

  • Warning

    The body is about 5,044 tokens (approx.); the spec suggests under 5,000. B2

    Fix: Move detail into reference files that the agent reads only when needed.

  • Note

    There is no license field, so readers can't tell whether they may reuse the skill. O2

    Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

• Claude CodePasses

  Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

  • Note

    The name "Agent Cost Report" doesn't match its folder "agent-cost-report". Claude Code shows the skill as /Agent Cost Report, and the folder name also invokes it. N4

    Fix: Set name: agent-cost-report, or rename the folder to agent-cost-report.

  • Note

    The body is about 5,044 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2

    Fix: Move detail into reference files that the agent reads only when needed.

• Claude apps & API uploadFails

  Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

  • Error

    The name "Agent Cost Report" has uppercase letters and spaces. Anthropic's validator allows only lowercase letters, digits and hyphens. N3

    Fix: Use name: agent-cost-report.

  • Error

    The name "Agent Cost Report" doesn't match its folder "agent-cost-report". claude.ai refuses an upload whose folder name doesn't match the skill name. N4

    Fix: Set name: agent-cost-report, or rename the folder to agent-cost-report.

  • Note

    The description is 342 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

    Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Bash Read Write AskUserQuestion mcp__plugin_claude-mem_mcp-search__search mcp__plugin_claude-mem_mcp-search__timeline mcp__plugin_claude-mem_mcp-search__get_observations

  • Note

    The body is about 5,044 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2

    Fix: Move detail into reference files that the agent reads only when needed.

• OpenAI (Codex & API)Fails

  Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

  • Error

    The name "Agent Cost Report" has uppercase letters and spaces. OpenAI's upload follows the spec, which allows only a–z, 0–9 and hyphens. N3

    Fix: Use name: agent-cost-report.

  • Warning

    The name "Agent Cost Report" doesn't match its folder "agent-cost-report". OpenAI's own upload example uses a differently named folder, but the spec it follows says they must match. N4

    Fix: Set name: agent-cost-report, or rename the folder to agent-cost-report.

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Bash Read Write AskUserQuestion mcp__plugin_claude-mem_mcp-search__search mcp__plugin_claude-mem_mcp-search__timeline mcp__plugin_claude-mem_mcp-search__get_observations

• VS Code & CopilotPasses with warnings

  VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

  • Warning

    The name "Agent Cost Report" has uppercase letters and spaces. VS Code uses the folder name whenever the name differs from it. N3

    Fix: Use name: agent-cost-report.

  • Warning

    The name "Agent Cost Report" doesn't match its folder "agent-cost-report". VS Code uses the folder name, agent-cost-report, instead. N4

    Fix: Set name: agent-cost-report, or rename the folder to agent-cost-report.

  • Note

    allowed-tools is a list; the spec defines a space-separated string. O5

    Fix: Write it on one line: allowed-tools: Bash Read Write AskUserQuestion mcp__plugin_claude-mem_mcp-search__search mcp__plugin_claude-mem_mcp-search__timeline mcp__plugin_claude-mem_mcp-search__get_observations

52 files