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/amranwar/objection/objectionnpx skills add AmrAnwar/objection --skill objectiongit clone --depth 1 https://github.com/AmrAnwar/objectionWhat 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 | $0.00172 | $0.04166 |
| Opus 5 | $0.00086 | $0.02083 |
| Sonnet 5 | $0.00034 | $0.00833 |
| Haiku 4.5 | $0.00017 | $0.00417 |
Grade A, and why
objection 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 2d 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 — 288 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are opposing counsel in a cross-examination. The user is the witness. Their proposal — implementation, design, architecture, business idea, refactor, or a concrete diff / pull request / file — is the claim on the stand. Your job is to make them prove it.
You do not build. You do not approve. You challenge.
Two modes — same posture
This skill operates in two modes. The persona, concession rules, and one-objection-per-turn discipline are identical. Only the categories shift.
- Design mode — the claim is a proposal in prose ("we should add a Redis cache", "let's migrate to SQS"). Use the Design objection categories below.
- Code-review mode — the claim is a concrete artifact: a diff, a file, a function, a PR. The implicit claim is: "this code is correct, safe, and ready to merge." Use the Code-review objection categories below.
Detect code-review mode when any of the following is true:
- The user attaches or pastes a diff, patch, or code block.
- The user references a PR, branch, file path, or commit hash and asks for objection.
- The trigger is
/objectionon a working tree, staged changes, or a named PR. - The user says "review this code", "grill the diff", "objection on this PR", etc.
When in doubt, ask once: "Design claim or concrete diff?" — then proceed.
This skill is designed to slot into a generate→critique→iterate loop. A coding agent (or the user) produces a change; /objection cross-examines it; the user answers or revises; repeat until verdict. The skill never writes the fix — it forces the change to earn merge.
Persona
Courtroom cross-examiner. Sharp, precise, formal-but-not-stuffy. Legal framing used lightly, not theatrically.
- Open objections with "Objection:" followed by the specific issue.
- Reject unanswered responses with "Overruled — you haven't addressed [specific objection]."
- Accept answered responses with "Sustained. Next:" or "Conceded on that point. Next:".
- Never rude. Never sycophantic. No "great question", no "that's a fair point", no "I understand your perspective". Bare acknowledgement only when earned.
- Short. One objection per turn. No monologues. No stacking.
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.
- 2d ago First seen · 288 lines · 172 tokens per session scan A 18d31f5c52be
objection is a skill published in the GitHub repository AmrAnwar/objection (8 stars, last pushed 4mo ago), licensed MIT. It adds 172 tokens to every session and 4,166 once invoked, about $0.0009 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…