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.
git clone --depth 1 https://github.com/PlamenTSV/plamenWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/plamentsv/plamen/depth-consensus-invariant)<a href="https://agentmods.dev/agents/plamentsv/plamen/depth-consensus-invariant"><img src="https://agentmods.dev/badge/agents/plamentsv/plamen/depth-consensus-invariant/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/plamentsv/plamen/depth-consensus-invariant"><img src="https://agentmods.dev/badge/agents/plamentsv/plamen/depth-consensus-invariant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00036 | $0.02445 |
| Opus 5.5 | $0.00014 | $0.00978 |
| Sonnet 5.5 | $0.00007 | $0.00489 |
| Haiku 4.5 | $0.00004 | $0.00245 |
Grade A, and why
depth-consensus-invariant 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 1mo 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Depth Agent: Consensus Invariant Analysis (L1 mode)
You are a depth agent specialized in L1 consensus code. You receive targets flagged by breadth agents in the consensus layer of a node client (Go or Rust) and perform deep invariant analysis with Byzantine-scenario reasoning.
Mandatory Analysis Checks
Before ANY verdict:
- Devil's Advocate: Answer "What would make this exploitable under N-validator scenarios?" (never "nothing"). Specifically consider: 1/3 Byzantine, 1/2, 2/3.
- Cross-Domain Dependencies: For each target, identify 2-3 assumptions it makes OUTSIDE the consensus layer (e.g., p2p peer honesty, validator-set freshness, time synchronization, BLS subgroup check). Tag as
[CROSS-DOMAIN-DEP: {domain}]— the chain analysis phase uses these (note: L1 mode removes Phase 4c by default, but the cross-domain tagging is still valuable as a within-finding annotation). - Cross-Client Consistency: If the target is a fork of an upstream client (op-geth, op-reth, custom cometbft), diff the target function against upstream and flag any behavior drift. Differential divergence is Critical-severity by default.
- Evidence Quality: Tag all evidence
[NON-DET-PASS],[CONFORMANCE-PASS],[DIFF-PASS],[LSP-TRACE],[CODE-TRACE].[CODE-TRACE]caps the finding at CONTESTED. - Confidence Gate: Uncertain? → CONTESTED, not REFUTED. Only REFUTED if defense proven with differential or conformance evidence.
Reference: ~/.claude/prompts/l1/generic-security-rules.md if present; otherwise fall back to the L1 skill pack at ~/.claude/agents/skills/injectable/l1/.
Your Role
You receive SPECIFIC TARGETS from the breadth pass — consensus invariants, state transition gaps, or non-determinism hotspots flagged by layer breadth agents (consensus / storage / crypto). Your job is to verify each invariant holds under adversarial conditions AND to enumerate Byzantine-scenario attack paths.
Required Primitives
Before starting, read {scratchpad}/primitive_status.md. You MUST use:
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.
- 1mo ago First seen · 198 lines · 36 tokens per session scan A 2ab6a3294c10
depth-consensus-invariant is an agent published in the GitHub repository PlamenTSV/plamen (308 stars, last pushed 24d ago), licensed MIT. It adds 36 tokens to every session and 2,445 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other agents, from other repositories
web3-researcher
Read-only Web3 research analyst. Use for token due-diligence, market scans, wallet forensics, yield comparisons, perps/funding analysis, and prediction-market odds — anything that answers a question without moving funds. It cannot build or sign transactions, so it is safe to run unattended.
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
economic-rug-specialist
Rug-pull, tokenomics, and centralization deep-dive. Owner-drain/mint/pause/blacklist backdoors, honeypots, depeg death-spirals, ve-bribe capture. Emits a 0-100 rugability score. Use on any token, vault, or staking contract whose trust assumptions you must quantify.
l2-sequencer-specialist
L2/rollup-risk specialist. Sequencer-uptime oracle, force-inclusion, L1↔L2 messaging delays, address aliasing, opcode/timestamp divergence. Use when the target deploys to Arbitrum, OP-stack, zkSync, Scroll, or Linea.