Borrowing it
Nothing to install: this file belongs to gotgenes/pi-anthropic-auth. 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/gotgenes/pi-anthropic-auth/main/.pi/skills/edit-tool/SKILL.mdgit clone --depth 1 https://github.com/gotgenes/pi-anthropic-authWrote 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/gotgenes/pi-anthropic-auth/edit-tool)<a href="https://agentmods.dev/skills/gotgenes/pi-anthropic-auth/edit-tool"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/edit-tool/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/gotgenes/pi-anthropic-auth/edit-tool"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/edit-tool.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 | $0.00041 | $0.01152 |
| Opus 5.5 | $0.00016 | $0.00461 |
| Sonnet 5.5 | $0.00008 | $0.00230 |
| Haiku 4.5 | $0.00004 | $0.00115 |
Grade A, and why
edit-tool 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 1mo 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edit tool
Load this skill before a non-trivial edit: a batch, a scripted substitution, or a structural insertion.
Batches are atomic
A multi-edit Edit call is atomic: if one oldText fails to match, the whole batch is rejected and nothing is applied.
Each edits[] entry has exactly one oldText/newText — put a second replacement in a second array entry, never as oldText2/newText2.
Extra suffixed keys are silently ignored while the tool still reports Successfully replaced N block(s), so count reported blocks against intended edits.
After a rejection, re-apply every intended edit (not just the ones you retried) and run pnpm run check to confirm none were silently dropped — but tsc passes on a dropped import type removal (an unused type import is not an error), so re-read the affected region rather than trusting the check alone.
Anchoring on decorative or padded lines
When an edit's oldText would span a decorative comment rule (a long run of ─/═) or a width-padded table row, anchor on adjacent unique code lines rather than the padded span itself — miscounting it fails the whole atomic batch, and rumdl fmt does not re-pad tables for you.
When the rule line is itself the target (deleting a section header with its block), copy it from a fresh Read of that region — retyping the dash run is what fails the batch.
When the rule line must be rewritten (a new label, so the padding changes), Edit has nothing to copy — write the line programmatically ('─' * (78 - len(label))).
If you delete such a block by line number with sed, re-read the region afterward to confirm you did not remove an enclosing brace.
An oldText spanning any non-ASCII character (an em-dash, a box-drawing rule, an ellipsis) must be copied from a fresh Read, never retyped: the character can be emitted as a bare newline, and the batch then fails on text you appear to have quoted correctly.
It can also land as an invisible \x0c form feed plus literal text (erence2, erence6), which a comment or a doc string carries past tsc, Biome, and the suite.
No gate in this repo catches it; see the markdown-conventions skill for the scan, the repair, and the placeholder workaround.
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.
- 1mo ago First seen · 48 lines · 41 tokens per session scan A db919396eb29
edit-tool is a skill published in the GitHub repository gotgenes/pi-anthropic-auth (426 stars, last pushed 13d ago), licensed MIT. It adds 41 tokens to every session and 1,152 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
pixiv-cli-ci
Diagnose pixiv-cli GitHub Actions failures and verify current-head quality, platform, PR-verification, native/browser, and release evidence. Use for CI readiness, failed or stalled runs, or an explicitly authorized rerun/cancel/dispatch; default to read-only evidence gathering.
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
agent-merge-conflict-arbiter
Neutral arbiter for merge conflicts between two agents.
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
reproduce-and-fix-issues
Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.