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 agentmods add skills/vinilana/dotcontext/sanitize-hook-payloadsnpx skills add vinilana/dotcontext --skill sanitize-hook-payloadsgit clone --depth 1 https://github.com/vinilana/dotcontextWrote 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/vinilana/dotcontext/sanitize-hook-payloads)<a href="https://agentmods.dev/skills/vinilana/dotcontext/sanitize-hook-payloads"><img src="https://agentmods.dev/badge/skills/vinilana/dotcontext/sanitize-hook-payloads.svg" alt="Measured on agentmods" 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 | $0.00062 | $0.00473 |
| Opus 5 | $0.00031 | $0.00236 |
| Sonnet 5 | $0.00012 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
sanitize-hook-payloads 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 6d 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.
What it actually says
Sanitize Hook Payloads
Treat host hook envelopes as untrusted, potentially huge, and potentially secret-bearing.
Workflow
- Trace the envelope from host stdin through normalization, mapping, and appendTrace.
- Set an input byte ceiling before parsing JSON.
- Reduce tool input to an allowlisted metadata summary before it reaches runtime state.
- Apply recursive redaction and serialized-size limits as defense in depth.
- Rotate traces by bytes and preserve atomic append behavior.
- Keep host hooks non-blocking while recording a bounded failure reason.
- Test equivalent envelopes for Claude Code, Codex, and Pi.
Tool summaries
- Write: keep path, byte length, hash, and contentOmitted.
- Edit: keep path, old/new lengths, hashes, and range metadata.
- Bash: keep classification, basename, and a bounded preview.
- Unknown: keep scalar metadata and key names only.
Redact content, old_string, new_string, patch, prompt, messages, authorization, tokens, passwords, secrets, and API keys case-insensitively.
Required invariants
- Never persist raw Write or Edit bodies.
- Never echo rejected stdin.
- Never rely only on host-provided sizes.
- Measure the serialized trace before writing.
- Keep trace rotation compatible with legacy trace.jsonl.
- Never delete the active segment.
- Keep safety ceilings effective even when configuration is malformed.
Dotcontext routing
- Keep host field mapping in src/integrations.
- Keep stdin limits in src/cli.
- Keep reusable sanitization and trace policy in src/harness.
- Update hook installer tests and public hook docs when observable behavior changes.
- Follow F-02.
Review gate
Verify a multi-megabyte Write produces a small trace, sensitive fixtures never appear on disk, oversized stdin stays non-blocking, rotation survives concurrent appends, and package smoke tests pass.
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.
- 6d ago First seen · 51 lines · 62 tokens per session scan A 35847a274186
sanitize-hook-payloads is a skill published in the GitHub repository vinilana/dotcontext (565 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 473 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…