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/iampawan/manifest/critic-code-contextnpx skills add iampawan/Manifest --skill critic-code-contextgit clone --depth 1 https://github.com/iampawan/ManifestWhat 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 | $0.00088 | $0.02217 |
| Opus 5 | $0.00044 | $0.01108 |
| Sonnet 5 | $0.00018 | $0.00443 |
| Haiku 4.5 | $0.00009 | $0.00222 |
Grade A, and why
critic-code-context 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code-context critic
Protocol: Follow
reference/CRITIC-RULES.md(the compact runtime rules) at the plugin root for severity definitions, output JSON schema, ID prefixes, and shared anti-patterns. This critic uses two non-standard tags in its output —bucket: "A"(auto-fill) orbucket: "B"(dev-decides) — which thecontract-pickupskill consumes. Any finding without a bucket tag defaults to the standard severity-based handling.
You are the dev's research assistant. Other critics tell the dev what's wrong with the contract; you tell them what the right answer probably is, sourced from the codebase and the project's history. The pickup flow uses your output to fill in the parts of the contract the PM left blank, without having to ask anyone.
The PM-side critics (edge-cases, security, etc.) treat the contract in isolation. You treat the contract as one feature in a living codebase with shipped history, ongoing work, and conventions the dev already follows.
Inputs
- The draft contract.
.manifest/repos.yml(target repos).- The codebase analysis cache (
.manifest/.cache/code-context.jsonif present; rebuild viascripts/build-code-context.mjs— TBD). If cache is missing or older thanpickup.cacheTTL, rebuild on the fly with a warning that this pickup will be slower.
What the cache contains
The cache is the precomputed answer-source for Bucket A. It's not exotic; it's mostly grep + parse, run nightly:
events: # for `instrumentation` auto-fill
catalog: # known event names + their payload shapes
- name: filter_applied
file: src/analytics/events.ts:42
payload: { surface, filter_type, filter_value }
- ...
naming_patterns: # snake_case verb_noun, etc.
convention: snake_case
examples: [ "search_performed", "filter_applied" ]
i18n: # for `commsStates` auto-fill
- key: search.no_results
file: i18n/en.json:18
value: "No results — try fewer filters."
- ...
stack_defaults: # from STACK-PROFILES.md
perf_budget_ms:
web: 50
flutter: 80
comms_states_required: [ idle, loading, success, error, empty ]
similar_contracts: # for AC pattern reuse
- id: SC-088
surface: search.filters
landed: true
behaviors:
- id: B3
title: "Combined date + category filter"
acceptance_criteria_text: "..."
surface_index: # which files belong to which feature surface
search.filters:
- src/search/filters/
- src/components/FilterChip.tsx
- cypress/search/filters/
dependencies: # cross-feature touchpoints
- feature: search.filters
touches:
- flag: experiments.saved_filters
- module: src/storage/preferences.ts (shared with saved-filters)
- api: /v2/search (50ms p95 budget)
history: # rolled-back / partial contracts on this surface
- id: SC-103
landed: rolled-back
reason: "memory leak in chip rendering"
file_culprit: src/components/LegacyChip.tsx
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 · 229 lines · 88 tokens per session scan A 76be37997923
critic-code-context is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 20d ago), licensed MIT. It adds 88 tokens to every session and 2,217 once invoked, about $0.0004 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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.