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/verified-zkevm/evm-asm/roadmap-4ch8fgit clone --depth 1 https://github.com/Verified-zkEVM/evm-asmWrote 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/verified-zkevm/evm-asm/roadmap-4ch8f)<a href="https://agentmods.dev/agents/verified-zkevm/evm-asm/roadmap-4ch8f"><img src="https://agentmods.dev/badge/agents/verified-zkevm/evm-asm/roadmap-4ch8f.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.04273 |
| Opus 5 | $0.00000 | $0.02136 |
| Sonnet 5 | $0.00000 | $0.00855 |
| Haiku 4.5 | $0.00000 | $0.00427 |
Grade A, and why
roadmap-4ch8f 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The 4ch8f roadmap — how to take run_stateless_guest verification to conclusion
Audience: the agent (any capability tier) picking up the next bead of epic
evm-asm-4ch8f. This page is the map; it tells you which bead to pick, which
recipe applies, which gates you must run, and where every load-bearing
definition lives. Read it top-to-bottom once; afterwards jump via §7.
The goal, in one sentence: prove
runStatelessGuestSound cr fuel fr execute (EvmAsm/Stateless/EntrySpec.lean)
for the real guest image — every routine of the RISC-V stateless_guest
replaced by a verified triple — while the empirical harness
scripts/codegen-eest-stateless-check.sh (EEST conformance,
[email protected] fixtures) keeps passing at every step.
Companion pages (do not duplicate their content; link into them):
docs/agents/port-playbook.md— the per-routine port workflow (kit → spec → proof →port-check.sh). This is the recipe for ~80 % of remaining beads.docs/agents/review-playbook.md— how to review a 4ch8f PR (the gates CI does NOT run, the adversarial checklists, the known-hole catalog).docs/agents/top-theorem-ledger.md— obligation rows from the statement down; update rows as beads close.docs/4ch8f-top-spec.md(the statement + trust boundary),docs/4ch8f-interp-strategy.md(interpreter/dispatch/frames),docs/4ch8f-crypto-strategy.md(crypto kernels + field-arith library),docs/sasm-design.md(the SAsm framework itself),docs/agents/proof-patterns.md+docs/agents/tactics-deep.md(tactic craft).
1. The layer DAG (verify callee-first, bottom-up)
L0 DONE machine model + accelerators (.1), SAsm core (.2-.5, .10 machinery),
layout + phase model (.6), asm→Program conversions (.9, 384 defs),
statement (.8), all strategy decisions (.7, .10, .11)
L1 leaf ports .12 .13 .14 .15 .16 .20 .23 .24 (+.17 .18 hash bridges)
L2 mid composites .19 .21 .22 .25 .26 .27 .35 .36 .37 (decode/extract/gas)
L3 state + MPT .28 .29 .30 .31 .32 (walk -> mutation -> roots)
L4 headers + chain .33 .34
L5 crypto track .38 -> .39 .40 -> .57 -> .58 (order: 4ch8f-crypto-strategy §5)
L6 interpreter .49 (loop) .50-.55 (handler families) .56 (frames)
L7 tx + verdict .41-.48 .59 .60 .61 .62
L8 shell + top .63 -> .64
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 Changed · +1 lines 267b1f70dc43
- 6d ago First seen · 217 lines · 0 tokens per session scan A 6b7f9296273c
roadmap-4ch8f is an agent published in the GitHub repository Verified-zkEVM/evm-asm (55 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,273 tokens. 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
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.