Stats
Actions
Available In
Tags
Plugin
pratyaksha-context-eng-harness
Long-context discipline for Claude Code: Avacchedaka-typed retrieval, sublation, witness-consciousness invariants, event-boundary compaction, and Khyātivāda hallucination classification. 15 MCP tools, 3 skills, 3 agents, 4 commands, 3 hooks.
What's Inside
Slash Commands4
/budget
/budget
Show local token budget gauge plus recent cost ledger entries (per-model totals, last N calls). Optionally reset the gauge.
/compact-now
/compact-now
Force a boundary-triggered compaction on the recent conversation window with optional scope (qualificand, task_context) and z-score threshold.
/context-status
/context-status
Show current state of the Pratyakṣa context store — qualificand surface, per-bucket counts, mean precisions, witness invariant token count, and recent ledger spend.
/sublate
/sublate
Manually sublate (bādha) one element by another, or sublate with new evidence. Refuses if newer precision does not strictly exceed older.
Agents3
buddhi
/buddhi
Slow/deliberate verifier subagent. Ratifies or rejects a Manas draft by fresh tool calls, sublates contradicted store elements, inserts new evidence with calibrated precision, and produces the final user-facing answer. Use when `manas` returns `needs_buddhi: true`, when the user asks for citations or certainty, or when a previously-unverified draft is about to drive a side-effecting action.
manas
/manas
Fast/intuitive draft subagent. Produces a first-pass answer cheaply using only the typed context store and the witness invariant. Use when the user asks a question that can plausibly be answered from existing knowledge, before paying the cost of full verification with `buddhi`.
sakshi-keeper
/sakshi-keeper
Witness-invariants enforcer. Owns the session Sākṣī. Use at session start to derive the witness invariant from the workspace `CLAUDE.md` and the user's first turn, whenever the user declares a new hard project rule, whenever an active hypothesis or contract enters scope, and as a periodic audit during long sessions to confirm the invariant has not silently drifted.
Skills3
witness-prefix
/witness-prefix
Use at session start to capture the session-stable invariant (Sākṣī) — user identity, project hard rules, the active hypothesis or contract under test — and ensure it is pushed as a real Claude `system` message at every model call. Use whenever the user changes the project, switches contexts, or states a new hard constraint that must persist across all subsequent reasoning.
context-discipline
/context-discipline
Discipline for long-context Claude Code sessions. Use when the working session crosses ~30k tokens, when the agent is about to consume retrieval results, when a tool produces multi-file output that may contain stale claims, or when the user asks for "what do we know about X right now" — anywhere implicit context drift would silently corrupt subsequent reasoning.
sublate-on-conflict
/sublate-on-conflict
Use when the agent encounters two retrieved claims that contradict each other, when fresh tool output disagrees with a previously-stored claim, when the user corrects an earlier statement, or when `detect_conflict` flags a pair. Resolves the conflict via sublation (precision-weighted overwrite with audit trail) instead of silent deletion or arbitrary tie-breaking.
Stats
Version2.0.0
Released
LanguagePython
Stars1
MaintenanceGood
LicenseMIT
Last Commit
Added
Available In
Safety Signals
Critical
Admin access level
Server config contains admin-level keywords
