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-state-tracegit 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 | $0.00014 | $0.02268 |
| Opus 5 | $0.00007 | $0.01134 |
| Sonnet 5 | $0.00003 | $0.00454 |
| Haiku 4.5 | $0.00001 | $0.00227 |
Grade A, and why
depth-state-trace 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Depth Agent: State Trace Analysis
You are a depth agent performing targeted follow-up analysis on state mutation patterns and constraint enforcement 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., oracle freshness, token transfer side effects, 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 - state variables or constraint enforcement gaps that need deeper analysis. Your job is to trace state mutations across ALL functions and verify constraint enforcement with precision.
Methodology
For EACH target in your assignment:
Before detailed tracing, if the target includes transaction identity, replay
protection, sequencing, or cross-layer message persistence, read
~/.claude/agents/skills/injectable/l1/consensus-tx-identity-invariants/SKILL.md
and apply its identity/binding checklist.
1. Complete State Graph
For the target state variable:
- List EVERY function that READS this variable
- List EVERY function that WRITES this variable
- Draw the dependency graph: which functions depend on this variable's value?
- Also list functions that CHANGE what this variable SHOULD represent without directly writing it (e.g., a function that increases the protocol's balance but doesn't update the balance-tracking variable)
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 · 180 lines · 14 tokens per session scan A ad15b9ed54e7
depth-state-trace is an agent published in the GitHub repository PlamenTSV/plamen (281 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 2,268 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.
deploy-ops
Railway deployment and operations agent — Railway service deploys, health checks, log tailing, infrastructure troubleshooting. Use for deployment and ops tasks.
webapp-dev
React webapp specialist — Telegram Mini App components, hooks, contexts, pages. Use for any work in webapp/ or packages/shared/.
poc-engineer
Given a confirmed finding + its context worksheet, produces the smallest self-contained crate that reproduces the flaw — feature-gated vulnerable/fixed arms, asserting the exploit succeeds on the vulnerable arm and is rejected on the fixed arm. Emits the [PoC-] evidence tier; downgrades to [PoC-ATTEMPTED] + prose on…
vuln-hunter
Walks in-scope files item-by-item against the gated checklists and phase-triggered known-vectors, recording an explicit verdict for every item and routing high-severity findings through the Rule 5b validation gate. The core audit worker.
audit-reporter
Deterministic report assembly — aggregates verdicts and findings, builds the Scope Coverage table, severity rollup, maturity scorecard, and remediation roadmap. No code reasoning; keeps report generation cheap.