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/pre-completion/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/pre-completion)<a href="https://agentmods.dev/skills/gotgenes/pi-anthropic-auth/pre-completion"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/pre-completion/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/pre-completion"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/pre-completion.svg" alt="Reviewed on agentmods" width="80" 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 Agent Snooping · line 48 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00046 | $0.01133 |
| Opus 5.5 | $0.00018 | $0.00453 |
| Sonnet 5.5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
pre-completion scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 29d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: pre-completion
Load this skill when all implementation steps are complete and the final deterministic checks have passed. Follow these steps in order before moving to "Summarize" and "Write stage notes."
Step 1: Gather context
Run from the repo root:
BASE=$(git describe --tags --abbrev=0 2>/dev/null || git rev-list --max-parents=0 HEAD)
git diff --name-only $BASE..HEAD
When the last tag predates unrelated already-landed work (this repo batches releases — refactor:/test:/build: commits don't tag), $BASE..HEAD over-scopes to sibling issues' shipped files.
Scope to the issue's own commits instead — anchor on the plan commit (docs: plan … (#N)): git diff --name-only <plan-commit>^..HEAD.
Note:
- The list of modified files.
- The issue number (from the plan frontmatter
issue:field or the plan filename patternNNNN-). - The plan file path (
docs/plans/NNNN-*.mdmatching the issue number; may be absent for unplanned work). - The base ref the reviewer's decision surface reads: the plan commit's parent (
<plan-commit>^), ororigin/mainwhen there is no plan commit. Resolve it to a SHA withgit rev-parserather than passing the^expression, so the reviewer runs one command with no shell quoting of its own.
Step 2: Dispatch the reviewer
Dispatch the pre-completion-reviewer subagent via the subagent tool:
subagent_type:"pre-completion-reviewer"description:"Pre-completion review for issue #N"prompt: include the issue number, the modified-files list from Step 1, the plan file path, and the base ref.
Example prompt to pass:
Review issue #46.
Plan file: docs/plans/0046-background-agent-coverage-gap.md
Base ref: 4e6c3a7a
Modified files since last tag:
.pi/agents/pre-completion-reviewer.md
.pi/skills/pre-completion/SKILL.md
.pi/prompts/tdd-plan.md
src/oauth-transport.ts
AGENTS.md
When the change removes or narrows a guard, add a re-derivation mandate to the prompt: name the invariants to verify, and require the reviewer to enumerate its own candidate inputs rather than check the ones the tests already cover.
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.
- 29d ago Changed · +1 lines 195bbbefa242
- 1mo ago Changed · +15 lines · -16 tokens per session aa5c4896044c
- 2mo ago First seen · 83 lines · 62 tokens per session scan A a4684a54dd36
pre-completion is a skill published in the GitHub repository gotgenes/pi-anthropic-auth (426 stars, last pushed 13d ago), licensed MIT. It adds 46 tokens to every session and 1,133 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 2026-08-30.
Other skills, from other repositories
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
pixiv-cli-pr
Prepare, update, or verify a pixiv-cli pull request using its current template, trusted verification policy, reviewed diff, and head-specific check results. Use for contributor handoff or PR readiness; merging, live /test execution, and releases are separate actions.
claude-md-improver
Audit and improve existing CLAUDE.md files across a repository. Use for a deliberate, repo-wide quality review—not to record learnings from the current session.
review-harness
Use when reviewing implementation work that ran through a /tmp Pi task harness. Checks contract drift, unsafe shortcuts, validation evidence, and status honesty.
claude-md-revision
Record durable, project-specific learnings from the current session in CLAUDE.md, .claude.local.md, or AGENTS.md—not general documentation, session summaries, or repo-wide audits.