Chalk Labs
Need help deploying anvi?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mrityunjaybhardwaj-anvi
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/anvi
What's inside
- Skill name
anvi- Description
- Activate the Ānvīkṣikī cognitive operating system. Applies epistemological discipline to all reasoning — diagnose bugs via causal chain analysis, design with ownership and lifecycle mapping, review with structural validation, recover from cascading failures via controlled retreat. Works standalone or as a layer under GSD.
- License
- GPL-3.0
- Instructions
- 64 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (200)
- tests.yml · .github/workflows/
- .gitignore
- BUILD_v1.md
- CHANGELOG.md
- ENFORCE.md
- LICENSE
- PROJECT_MANAGEMENT.md
- README.md
- SKILL.md
- STORAGE.md
- SYSTEM_ARCHITECTURE.md
- VERSION
- anvi-advisor-researcher.md · agents/
- anvi-checker.md · agents/
- anvi-codebase-mapper.md · agents/
- anvi-debugger.md · agents/
- anvi-executor.md · agents/
- anvi-integration-checker.md · agents/
- anvi-nyquist-auditor.md · agents/
- anvi-planner.md · agents/
- anvi-project-researcher.md · agents/
- anvi-research-synthesizer.md · agents/
- anvi-researcher.md · agents/
- anvi-roadmapper.md · agents/
- anvi-ui-auditor.md · agents/
- anvi-ui-checker.md · agents/
- anvi-ui-researcher.md · agents/
- anvi-user-profiler.md · agents/
- anvi-verifier.md · agents/
- AnviDeck.jpg · assets/
- DyzenAI.jpg · assets/
- FlipFace.jpg · assets/
- MohMayaOS.jpg · assets/
- SonicWeb.png · assets/
- stave.png · assets/
- anvi-tools.cjs · bin/
- LICENSE.GSD · bin/lib/
- VENDORED.md · bin/lib/
- commands.cjs · bin/lib/
- config.cjs · bin/lib/
- core.cjs · bin/lib/
- frontmatter.cjs · bin/lib/
- init.cjs · bin/lib/
- milestone.cjs · bin/lib/
- model-profiles.cjs · bin/lib/
- phase.cjs · bin/lib/
- profile-output.cjs · bin/lib/
- profile-pipeline.cjs · bin/lib/
- roadmap.cjs · bin/lib/
- security.cjs · bin/lib/
- state.cjs · bin/lib/
- template.cjs · bin/lib/
- uat.cjs · bin/lib/
- verify.cjs · bin/lib/
- adaptive-observation.md · cognitive-os/
- base-layer.md · cognitive-os/
- context-rot.md · cognitive-os/
- dharana-spec.md · cognitive-os/
- dhyana-spec.md · cognitive-os/
- design.md · cognitive-os/modes/
- …and 140 more
SKILL.md (first lines)
# Ānvīkṣikī — Cognitive Operating System ## Loading When this skill activates, load these files into context: 1. `~/.claude/anvi/cognitive-os/base-layer.md` — always-active checks 2. `~/.claude/anvi/cognitive-os/translation.md` — output translation rules 3. `~/.claude/anvi/cognitive-os/context-rot.md` — compression protocol Load lenses on demand (when the situation calls for them): - `~/.claude/anvi/cognitive-os/modes/diagnose.md` — something is broken - `~/.claude/anvi/cognitive-os/modes/design.md` — building something new - `~/.claude/anvi/cognitive-os/modes/review.md` — checking existing work - `~/.claude/anvi/cognitive-os/modes/recover.md` — stuck or cascading failure Load project-specific catalogues if they exist (`.anvi/` in project root): - `.anvi/hetvabhasa.md` — project error patterns - `.anvi/vyapti.md` — project invariants - `.anvi/krama.md` — project lifecycle patterns ## Behavior When Active ### Base layer runs silently on every action: - **Sequence check:** Am I assuming sync when this might be async? - **Witness check:** Am I discriminating or reacting? - **Completion check:** Has the insight been found? If so, ship it. - **Existence check:** Do I understand what exists before changing it? - **Observation check:** What did I directly observe that proves this works? - **Completeness check:** Can I state the full argument? (behavioral changes only) - **Reactivity check:** Is this fix driven by insight or urgency? - **Reception check:** User corrected my framing — adopt it first, verify second. - **Translation check:** Internal concepts stay internal. Output in user's language. ### Lenses apply based on context: - Debugging → diagnose lens (gather → classify → scan → compress → prove → fix) - Building → design lens (ownership → lifecycle → entanglement → depth → pre-mortem) - Reviewing → review lens (existence → Beck → auditability → observation → susceptibility) - Stuck → recover lens (stop → compress → revert → receive → re-enter) ### All output passes through the translation layer: - Internal reasoning uses Sanskrit terms for precision - Output translates to user profile language or plain English - Framework terminology is NEVER exposed to the user ## Copilot Integration When used from VS Code Copilot Chat (no native hook mechanism, so this must be loaded explicitly — see `copilot-compat/README.md` for the three load paths): - `~/.claude/anvi/copilot-compat/executor-hook.md` - `~/.claude/anvi/copilot-compat/planner-hook.md` - `~/.claude/anvi/copilot-compat/checker-hook.md` - `~/.claude/anvi/copilot-compat/debugger-hook.md` ## Project Initialization To create project-specific catalogues: ```bash ~/.claude/anvi/install.sh # select "Initialize project catalogues" ``` Or manually: copy templates from `~/.claude/anvi/references/*-template.md` to `.anvi/` and rename (drop `-template`).
From MrityunjayBhardwaj/anvi, GPL-3.0.
More from MrityunjayBhardwaj/anvi
- 0.552score
anvi:explore
MrityunjayBhardwaj
Explore a friction point — when something doesn't exist that should.
SkillAFreshness: AClaude Code +9 - 0.552score
anvi:debug
MrityunjayBhardwaj
Systematic debugging with the cognitive OS.
SkillAFreshness: AClaude Code +9 - 0.512score
anvi:currency
MrityunjayBhardwaj
Check catalogue freshness — which entries have drifted from the code they point at — and re-validate them.
SkillBFreshness: BClaude Code +9 - 0.398score
anvi:audit
MrityunjayBhardwaj
Run self-coherence audit on the framework's project catalogues.
SkillDFreshness: DClaude Code +9 - 0.398score
anvi:do
MrityunjayBhardwaj
Route freeform text to the right Anvi command automatically.
SkillDFreshness: DClaude Code +9 - 0.393score
anvi:execute-phase
MrityunjayBhardwaj
Execute all plans in a phase with wave-based parallelization and cognitive OS checks.
SkillDFreshness: DClaude Code +9 - 0.393score
anvi:discuss-phase
MrityunjayBhardwaj
Gather phase context through adaptive questioning before planning.
SkillDFreshness: DClaude Code +9 - 0.393score
anvi:complete-milestone
MrityunjayBhardwaj
Archive completed milestone and prepare for next version.
SkillDFreshness: DClaude Code +9 - 0.390score
anvi:fast
MrityunjayBhardwaj
Execute a trivial task inline with no subagents or planning overhead.
SkillDFreshness: DClaude Code +9 - 0.387score
anvi:audit-uat
MrityunjayBhardwaj
Cross-phase audit of all outstanding UAT and verification items
SkillDFreshness: DClaude Code +9 - 0.387score
anvi:audit-milestone
MrityunjayBhardwaj
Audit milestone completion against original intent before archiving
SkillDFreshness: DClaude Code +9 - 0.387score
anvi:cleanup
MrityunjayBhardwaj
Archive accumulated phase directories from completed milestones
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 42
- Last commit
- Oct 20, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- Repository
- github.com/MrityunjayBhardwaj/anvi
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from MrityunjayBhardwaj
- 0.552score
anvi:explore
MrityunjayBhardwaj
Explore a friction point — when something doesn't exist that should.
SkillAFreshness: AClaude Code +9 - 0.552score
anvi:debug
MrityunjayBhardwaj
Systematic debugging with the cognitive OS.
SkillAFreshness: AClaude Code +9 - 0.512score
anvi:currency
MrityunjayBhardwaj
Check catalogue freshness — which entries have drifted from the code they point at — and re-validate them.
SkillBFreshness: BClaude Code +9 - 0.398score
anvi:do
MrityunjayBhardwaj
Route freeform text to the right Anvi command automatically.
SkillDFreshness: DClaude Code +9 - 0.398score
anvi:audit
MrityunjayBhardwaj
Run self-coherence audit on the framework's project catalogues.
SkillDFreshness: DClaude Code +9 - 0.393score
anvi:discuss-phase
MrityunjayBhardwaj
Gather phase context through adaptive questioning before planning.
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get anvi running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
anvi skill. Agent Mart. https://agentmart.dev/skills/mrityunjaybhardwaj-anvi (last updated 2026-10-24)