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 skills add seeker71/Coherence-Network --skill walk-g1-g7git clone --depth 1 https://github.com/seeker71/Coherence-NetworkWrote 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/skills/seeker71/coherence-network/walk-g1-g7)<a href="https://agentmods.dev/skills/seeker71/coherence-network/walk-g1-g7"><img src="https://agentmods.dev/badge/skills/seeker71/coherence-network/walk-g1-g7/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/skills/seeker71/coherence-network/walk-g1-g7"><img src="https://agentmods.dev/badge/skills/seeker71/coherence-network/walk-g1-g7.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 | $0.00183 | $0.00645 |
| Opus 5 | $0.00092 | $0.00322 |
| Sonnet 5 | $0.00037 | $0.00129 |
| Haiku 4.5 | $0.00018 | $0.00064 |
Grade A, and why
walk-g1-g7 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 12d 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.
What it actually says
walk-g1-g7 — build the tower with only form-cli
The discipline: only form-cli subcommands. No hand-written recipes, no Edit/Write,
no remote LLM unless the loop itself escalates. Local oracle is ollama run coder
(or qwen2.5:72b); the remote tier is claude -p and every use of it is COUNTED.
The loop, per open step
form-cli roadmap # the plan; read the next open step + its spec
form-cli asm "<C for the construct>" # learn LLVM's lowering offline (clang, local)
form-cli close "<id>" "<spec informed by the asm>" "<assert>" "<expected>" "ollama run coder"
# close: a LOCAL oracle drafts the recipe; the kernel validates it against the assert.
# if it validates -> register a band + run: cd form/form && ./validate.sh ... (four-way) -> ship.
# if it does not -> record WHY, do not hand-write the fix; the point is to find what
# form-cli itself still lacks.
What to measure and report
- remote calls: count every time the loop used
claude -p(target: 0). - shipped: how many steps produced a four-way-validated recipe via form-cli alone.
- for each not shipped: the exact reason (the kernel error, the missing capability), and the smallest fix to form-cli that would let it ship next time.
The honest frame
A step "shipped via form-cli" only if a form-cli command (not the operator) produced
the validated recipe. If the operator had to write the recipe by hand, that step did
NOT ship via form-cli — record it as a gap in form-cli and name the fix. The report's
value is the gap list + fixes, not a green count.
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.
- 12d ago First seen · 45 lines · 183 tokens per session scan A 0d34c6ea5c3e
walk-g1-g7 is a skill published in the GitHub repository seeker71/Coherence-Network (3 stars, last pushed 2d ago), licensed Apache-2.0. It adds 183 tokens to every session and 645 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
llvm-learning
Comprehensive learning resources and tutorials for LLVM, Clang, and compiler development. Use this skill when helping users learn LLVM internals, find educational resources, or understand compiler concepts.
cpp-mentor
A general, self-adapting C++ mentor for any project. On first run with an empty profile it onboards: settles the goal and domain, derives a namespace from the goal, agrees conventions including the project's own error policy, and audits the developer's level in both C++ and the project's topic — with questions…
automotive-examples-code
Production-ready automotive code examples from automotive-claude-code-agents. Includes BMS ECU firmware (C), ADAS perception pipeline (Python), battery thermal modeling, network topologies, multi-region cloud deployment (Terraform/K8s), and automotive protocol demos. Use when the user wants real working code for…
leetcode-helper
Expert LeetCode problem solver for optimized C++ coding interview solutions. Use when: the user pastes a LeetCode problem, asks for an optimized algorithm, wants C++ LeetCode code, needs a dry run, asks for line-by-line explanation, wants a hint before the solution, wants brute force to optimized progression, wants…
developer-assembly-x86-fundamentals
Fundamentos x86/x64 — modos de endereçamento, segmentos, modo real vs protegido. Independente de assembler.
zoom-meeting-sdk-unreal
Zoom Meeting SDK for Unreal Engine wrapper integrations. Use when building Unreal projects that embed Zoom meetings with C++ and Blueprint wrappers, including wrapper-to-SDK mapping concerns.