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.
npx skills add getklaim/claude-auto-context --skill create-suggestiongit clone --depth 1 https://github.com/getklaim/claude-auto-contextWrote 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/getklaim/claude-auto-context/create-suggestion)<a href="https://agentmods.dev/skills/getklaim/claude-auto-context/create-suggestion"><img src="https://agentmods.dev/badge/skills/getklaim/claude-auto-context/create-suggestion/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/getklaim/claude-auto-context/create-suggestion"><img src="https://agentmods.dev/badge/skills/getklaim/claude-auto-context/create-suggestion.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 | $0.00036 | $0.01037 |
| Opus 5 | $0.00018 | $0.00518 |
| Sonnet 5 | $0.00007 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
create-suggestion 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 8d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Suggestion
Analyze session data to detect structural issues and create proposal files requiring user approval before applying.
Qualification Criteria
Structural problems evidenced by session data:
- File bloat: A file is read frequently but only small portions used per session (low signal ratio)
- Pattern fragmentation: Multiple files doing the same thing differently
- Directory misorganization: Logically related files scattered across directories
- Missing abstractions: Same code pattern repeated in 3+ places without extraction
Evidence Requirements
Every suggestion MUST include:
- Quantitative metrics (signal ratio, read count vs edit count, etc.)
- Specific session IDs as evidence
Output Format
Create files in .claude-auto-context/suggestions/ as suggestion-YYYYMMDD-HHMMSS-{slug}.md:
# Suggestion: {title}
## Description
{one-line summary — used for deduplication and context display}
## Status
pending
## Created
{ISO 8601 UTC timestamp, e.g. 2026-03-27T14:30:52Z}
## Category
{ai-unfriendly-large-file | ai-unfriendly-naming | ai-unfriendly-missing-docs | ai-unfriendly-structure | ai-unfriendly-fragile}
## Problem
{Description with quantitative evidence and specific file names}
## Related Files
- {file1.ext} — {why this file is involved}
- {file2.ext} — {why this file is involved}
## Proposal
### Read first
- {file1.ext} — {why executor must read this before changes, e.g. "contains function to extract"}
- {file2.ext} — {dependency or convention reference}
### Files to modify
- {file1.ext} — {what changes in this file}
- {file2.ext (new file)} — {what this new file will contain}
### Changes
1. In {file1.ext}, function `{functionName}` (lines ~{N}-{M}):
- {specific operation: extract, rename, move, delete, modify}
- {import/export updates needed after the change}
2. In {file2.ext (new file)}:
- Create with exports: {exportName1}, {exportName2}
- Import dependencies: {dep1} from {source}
### Impact
- {other-file.ext} — imports from {file1.ext}, import path may need update
- {test-file.ext} — test assertions may reference moved functions
### Acceptance criteria
- [ ] `grep -q '{exportName}' {new-file.ext}` — export exists in new location
- [ ] `grep -q 'from.*{new-file}' {file1.ext}` — import path updated
- [ ] No TypeScript/syntax errors in modified files
- [ ] Existing tests pass without modification (or test updates documented)
## Evidence Sessions
- session_{id} ({date}): {what was observed}
## Metrics
- Signal ratio: {X}%
- Sessions affected: {N}/{total}
- Estimated impact: {description}
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.
- 8d ago First seen · 116 lines · 36 tokens per session scan A 3935cbcb2b21
create-suggestion is a skill published in the GitHub repository getklaim/claude-auto-context (10 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 1,037 once invoked, about $0.0002 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…