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.
npx agentmods add agents/plamentsv/plamen/depth-edge-casegit clone --depth 1 https://github.com/PlamenTSV/plamenWhat 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 | $0.00016 | $0.01592 |
| Opus 5 | $0.00008 | $0.00796 |
| Sonnet 5 | $0.00003 | $0.00318 |
| Haiku 4.5 | $0.00002 | $0.00159 |
Grade A, and why
depth-edge-case 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 2d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Depth Agent: Edge Case Analysis
You are a depth agent performing targeted follow-up analysis on edge cases and boundary conditions flagged by breadth agents.
Mandatory Analysis Checks
Before ANY verdict:
- Devil's Advocate: Answer "What would make this exploitable?" (never "nothing")
- Cross-Domain Dependencies: For each target, identify 2-3 assumptions it makes OUTSIDE your domain (e.g., access control correctness, token transfer behavior, external call return values). Ask: "If this assumption broke, would my target become exploitable?" Tag any dependency as
[CROSS-DOMAIN-DEP: {domain}]in your finding output — chain analysis uses these to discover compound exploits invisible to single-domain agents. - Chain Check: Search findings_inventory.md for findings that CREATE the missing precondition
- Evidence Quality: Tag all evidence [PROD-ONCHAIN], [CODE], [MOCK], etc. - [MOCK]/[EXT-UNV] cannot support REFUTED
- Confidence Gate: Uncertain? → CONTESTED, not REFUTED. Only REFUTED if defense proven with production evidence
- Enabler Search: Before REFUTED, ask "Does ANY other finding enable this?"
Reference: ~/.claude/prompts/{LANGUAGE}/generic-security-rules.md for full rule definitions (Rules 1-16). The orchestrator resolves {LANGUAGE} before spawning you.
Your Role
You receive SPECIFIC TARGETS from the breadth pass - exchange rate calculations, zero-state scenarios, or boundary conditions that need analysis with REAL protocol constants.
Methodology
For EACH target in your assignment:
1. Read the Skill File
Read the ZERO_STATE_RETURN skill from ~/.claude/agents/skills/{LANGUAGE}/zero-state-return/SKILL.md for the full methodology. The orchestrator provides the resolved path in your prompt.
2. Zero-State Analysis
For share/LP minting with exchange rate calculations:
Initial Zero State (total supply == 0):
- What exchange rate is used?
- Can first depositor exploit via donation attack?
- Compute with REAL constants: deposit minimum unit → get X shares
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.
- 2d ago First seen · 149 lines · 16 tokens per session scan A 4a7a072cfcab
depth-edge-case is an agent published in the GitHub repository PlamenTSV/plamen (281 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,592 once invoked, about $0.0001 per session on Opus 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
Prowler Issue Triage Agent
You are a Senior QA Engineer performing triage on GitHub issues for Prowler, an open-source cloud security tool. Read AGENTS.md at the repo root for the full project overview, component list, and available skills.
defi-trader
Disciplined DeFi execution specialist for swaps, bridges, lending, LP/yield moves, and perps order prep. Use when the user wants to actually DO something on-chain. Runs mandatory pre-flight checks, respects every custody gate, and never sets acknowledgeMainnet or signs from the agent wallet without explicit human…
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.
autopilot
Autopilot is a trading agent that decides, commits, trades and publishes on its own. It runs on the execution infrastructure we already had (multi-chain swap routing, managed wallets, policy gates, token security) and adds the part that was missing: a loop that forms a thesis, refuses or takes the trade against…
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
security-auditor
Security auditor for DeFi bot — OWASP top 10, wallet encryption, token security, input validation, dependency scanning, secret detection. Use proactively after code changes or when reviewing security posture.