PlamenTSV/plamen

fork-ancestry

Trigger Pattern Always (run during recon TASK 0, not breadth) - Inject Into Recon agent only (meta_buffer.md enrichment)

Langue du texte source : anglais

fork-ancestry

Trigger Pattern Always (run during recon TASK 0, not breadth) - Inject Into Recon agent only (meta_buffer.md enrichment)

Langue du texte source : anglais

stableswap-compliance

Trigger STABLESWAP_FORK flag (fork-ancestry detects Curve/StableSwap parent via get_d/get_y/ramp_a/StableSwap patterns) - Agent Type general-purpose (standalone niche agent, 1 budget slot)

Langue du texte source : anglais

fork-ancestry

Trigger Pattern Always (run during recon TASK 0, not breadth) - Inject Into Recon agent only (meta_buffer.md enrichment)

Langue du texte source : anglais

fork-ancestry

Trigger Pattern Always (run during recon TASK 0, not breadth) - Inject Into Recon agent only (meta_buffer.md enrichment)

Langue du texte source : anglais

fork-ancestry

Trigger Pattern Always (run during recon TASK 0, not breadth) - Inject Into Recon agent only (meta_buffer.md enrichment)

Langue du texte source : anglais

integration-hazard-research

Protocol Type Trigger NAMED_EXTERNAL_PROTOCOL (detected when recon finds import/interface for an identifiable external protocol — not standard libraries). Researches known integration hazards of the target protocol.

Langue du texte source : anglais

execution-client-hardening

L1 trigger - audits execution engine (EVM interpreter, WASM, SVM) for memory corruption, gas mispricing (EXTCODESIZE class), opcode semantics, and VM invariant breaks.

Langue du texte source : anglais

vault-accounting

Protocol Type Trigger vault (detected in recon TASK 0 Step 1) - Inject Into Core state agent OR economic design agent (merge via M4 hierarchy)

Langue du texte source : anglais

config-correctness

L1 trigger - audits configuration constants, documented bounds, feature-gated values, and unused protocol limits for semantic drift.

Langue du texte source : anglais

consensus-safety-invariants

L1 trigger - detects non-determinism, state transition completeness violations, and safety/liveness invariant breaks in consensus code. Inject into depth-consensus-invariant or depth-state-trace.

Langue du texte source : anglais

cosmos-ibc-security

L1 trigger - audits IBC / ibc-go cross-chain entry points for ICS-23 / Merkle proof gaps, ordered-channel sequence integrity, escrow burn<->mint synchronization, light-client version downgrade, and timeout/ack handler reentrancy.

Langue du texte source : anglais

cosmos-sdk-module-safety

L1 trigger - audits Cosmos-SDK / CometBFT modules for consensus non-determinism, unmetered ABCI hooks, signer/state mismatches, module-account bookkeeping breaks, sdk.Dec rounding, ABCI-path panics, unregistered Msg handlers, and fee/gas overflow.

Langue du texte source : anglais

cross-environment-semantic-drift

L1 trigger - audits L1/L2 boundary bugs, precompile context assumptions, integer width mismatches at environment boundaries, and EVM-on-non-EVM drift.

Langue du texte source : anglais

data-availability-enforcement

L1 supplement - audits storage / data-availability chains (Arweave / Celestia-class) for unenforced data commitments: producer commits to data inclusion but the validator never verifies the data was actually published / gossiped / sampled.

Langue du texte source : anglais

mempool-asymmetric-dos

L1 trigger - audits mempool / transaction pool for eviction asymmetries, replacement policy abuse, blob-pool exhaustion, and DETER-class denial of service.

Langue du texte source : anglais

rpc-surface-audit

L1 trigger - audits JSON-RPC and Engine API surfaces for authentication bypass, rate limiting, subscription buffer overflows, and method-specific DoS.

Langue du texte source : anglais

validator-lifecycle-and-slashing

L1 trigger - audits validator entry/exit transitions, slashing correctness, leader-duplicate handling, and lifecycle state invariants for PoS / DPoS / BFT consensus clients.

Langue du texte source : anglais

dimensional-analysis

Trigger MIXED_DECIMALS flag (mulDiv/mulWad/rayMul + mixed scale factors detected) - standalone niche agent, 1 budget slot

Langue du texte source : anglais

spec-compliance-audit

Trigger HAS_DOCS flag in template_recommendations.md (recon detects non-empty DOCS_PATH - whitepaper, spec, or design doc provided) - Agent Type general-purpose (standalone nich...

Langue du texte source : anglais

auth-validation

Trigger Pattern Always required for Soroban audits - Inject Into Breadth agents, depth agents

Langue du texte source : anglais

plamen

Launch the Plamen deterministic Web3 security audit pipeline

Langue du texte source : anglais

authorization-model

Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-state-trace, depth-external

Langue du texte source : anglais

choice-semantics

Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-state-trace, depth-edge-case

Langue du texte source : anglais

cid-capability-safety

Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-external, depth-edge-case

Langue du texte source : anglais

contract-key-safety

Trigger Pattern Always required for DAML audits (self-skips if no template defines a key) - Inject Into Breadth agents, depth-state-trace

Langue du texte source : anglais

economic-design-audit

Trigger Pattern MONETARY_PARAMETER flag (fee, rate, emission, cap, bps as template fields) - Inject Into Breadth agents (merged via M4 hierarchy)

Langue du texte source : anglais

ensure-invariants

Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-edge-case

Langue du texte source : anglais

locking-semantics

Trigger Pattern Always required for DAML audits (self-skips if no lock pattern present) - Inject Into Breadth agents, depth-state-trace, depth-edge-case

Langue du texte source : anglais

privacy-disclosure

Trigger Pattern Always required for DAML audits - Inject Into Breadth agents, depth-edge-case

Langue du texte source : anglais

semi-trusted-roles

Trigger Pattern operator/admin/manager parties listed as signatory or controller, authority-gated choices - Inject Into Breadth agents, depth-state-trace

Langue du texte source : anglais

share-allocation-fairness

Trigger Pattern SHARE_ALLOCATION flag detected in pattern scan - Inject Into Breadth agents, depth-edge-case

Langue du texte source : anglais

temporal-parameter-staleness

Trigger Pattern interval|period|duration|delay|cooldown|lock_period|timelock|deadline|maturity|expiry|getTime - Inject Into Breadth agents, depth-state-trace

Langue du texte source : anglais

verification-protocol

Trigger Pattern Always (used by all verifier agents) - Inject Into security-verifier agents (Phase 5)

Langue du texte source : anglais

token-flow-tracing

Performs comprehensive token flow analysis by tracing all token entry and exit paths, verifying accounting consistency, detecting unsolicited transfer vectors, and identifying risks such as donation attacks, balance desynchronization, token type confusion,…

Langue du texte source : anglais

semantic-consistency-audit

Trigger HAS_MULTI_CONTRACT flag in template_recommendations.md (recon detects 2+ in-scope contracts/modules sharing parameters or formulas) - Agent Type general-purpose (standal...

Langue du texte source : anglais

plamen-l1

Launch the Plamen deterministic L1 infrastructure audit pipeline

Langue du texte source : anglais

plamen-l1-wizard

Run the Plamen L1 infrastructure audit wizard in Codex

Langue du texte source : anglais

plamen-wizard

Run the Plamen smart-contract audit wizard in Codex

Langue du texte source : anglais

bls-aggregation-audit

L1 trigger - audits BLS signature aggregation: subgroup check, rogue-key attack defense, aggregation order, signing-domain separation.

Langue du texte source : anglais