No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →MECHANISM · CONTEXT · CORE
Instruction Discovery
Discover, order, bound, and attribute project instructions before model execution.
2 lessons0 agent snapshots0 experiments
contextinstruction-discoveryproblem → policy → evidence
L0Intuitioncomplete
L1Buildcomplete
L2Engineeringcomplete
L3Architecturemissing
L4Researchmissing
DEPENDENCY GRAPH · READER PATH
What feeds it, and what does it unlock?
Arrows show learning and design dependencies, not runtime data flow. Follow any node to continue through the Atlas.
Prerequisites
instruction-discoveryInstruction DiscoveryCurrent research boundary
Discover, order, bound, and attribute project instructions before model execution.
The structured record is in the Atlas, but the L0–L4 article has not passed content review.
AGENT MAPPING · EVIDENCE ONLY
Snapshot implementations
An implementation enters the map only when both a snapshot and claims exist; unknowns remain visible.
No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →No implementation currently clears the Snapshot + Claim threshold; this is not a claim that the product lacks the capability.
Inspect coverage boundary →CLAIMS · EVIDENCE LEDGER0 RECORDS
No reviewed Agent claims
The teaching-harness reference does not automatically become an architectural claim about any vendor agent.
EXPERIMENTS · EXERCISES
What has actually been tested?
Formal experiments are separate from course exercises. Exercises can validate the reference implementation but cannot replace Native evidence from a real agent.
Formal experiment · not registered
No experiment record means untested, not passed. The course checks below cover only the deterministic reference harness.
s05-instructionsobserve
Verify instruction inputThe run matches the committed trace without leaking a local absolute path.
python3 -m curriculum.golden verify s05-instructionss05-instructionsmodify
Test root-to-leaf precedenceRoot instructions remain before package instructions and an external cwd is rejected.
python3 -m unittest curriculum.tests.test_vertical_slice.VerticalSliceTests.test_s05_root_to_leaf_instructions curriculum.tests.test_vertical_slice.VerticalSliceTests.test_instruction_discovery_rejects_external_cwd -vs12-project-trustobserve
Verify instruction authorityPlatform/project sources are accepted while external/tool-output sources are quarantined outside the system prompt.
python3 -m curriculum.golden verify s12-project-trusts12-project-trustmodify
Test identity-bound trustChanging revision changes the fingerprint and does not inherit the old grant; keyword detection does not change authority.
python3 -m unittest curriculum.tests.test_vertical_slice.VerticalSliceTests.test_s12_keeps_untrusted_data_out_of_instruction_authority -v01
How should conflicting instruction scopes be surfaced to users and traces?