Borrowing it
Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/verify-claims-on-disk/SKILL.mdgit clone --depth 1 https://github.com/greenmtnsun/GitEasyWrote 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/greenmtnsun/giteasy/verify-claims-on-disk)<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/verify-claims-on-disk"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/verify-claims-on-disk/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/greenmtnsun/giteasy/verify-claims-on-disk"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/verify-claims-on-disk.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00154 | $0.01792 |
| Opus 5.5 | $0.00062 | $0.00717 |
| Sonnet 5.5 | $0.00031 | $0.00358 |
| Haiku 4.5 | $0.00015 | $0.00179 |
Grade A, and why
verify-claims-on-disk 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
See also:
software-creation§4 for the structured-result discipline that makes apply-claims inspectable in the first place.
Verify-claims-on-disk
When another session, handoff doc, or background process tells the current session that something was applied, verify before building on it. Apply-claims have failed twice in the last 7 days; treat them as proposals until disk confirms.
The current session's own recent edits are different — those have tool-result evidence in the same conversation. This skill is about trans-session trust.
Mechanized path (prefer this): if the handoff doc carries a ## Claims block (see the handoff skill), run Test-HandoffClaims.ps1 -HandoffPath <doc> from this skill's folder instead of hand-verifying — exit 0 = all claims match disk, exit 1 = drift, do not build on the handoff. The manual protocol below remains for claims made outside a handoff doc (chat messages, dispatch output, docs without a Claims block).
Trigger phrases
This skill activates when the conversation contains any of:
- "I applied X" / "applied the [fix | change | edit]"
- "I added [function | class | line | comment | test]"
- "I removed X" / "deleted X"
- "wrote [content] to [path]" / "saved [path]"
- "[file] now contains X" / "the change is in [file]"
- Any handoff doc claiming completed edits ("commit 1 landed", "Phase X complete", "shipped")
- Any apply-claim from a separate Claude session (dispatch-app, phone Claude, scheduled task, overnight loop)
- Any "before/after" comparison where the "after" wasn't observed in the current session
If the conversation includes a phrase like the above and the change isn't visible in the current session's tool history, run the verification protocol.
Verification protocol
Step 1 — Parse the claim into three things
| Field | Example |
|---|---|
| File path | C:\Sysadmin\Scripts\PesterForge\Public\Invoke-PesterForge.ps1 |
| Expected content | function Invoke-PesterForge (a symbol) OR a literal line excerpt |
| Operation | added / removed / modified / created / deleted |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 119 lines · 154 tokens per session scan A 32302d5e5b33
verify-claims-on-disk is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 154 tokens to every session and 1,792 once invoked, about $0.0006 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 2026-11-18.
verify-claims-on-disk compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| verify-claims-on-diskgreenmtnsun/GitEasy | Skill | 1 | yesterday | MPL-2.0 | A | 154 | Claude Code |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | today | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | yesterday | MIT | A | 71 | Claude Code, Codex |
| observability-audit-sessionsIBM/mcp-context-forge | Skill | 4.9k | today | Apache-2.0 | A | 64 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 333 | today | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | today | Apache-2.0 | A | 15 | Claude Code, Codex |
| diagnosing-missing-recordingsPostHog/posthog | Skill | 41k | today | none | A | 76 | Claude Code, Codex |