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 skills/hoangsonww/forge-agentic-coding-cli/fresh-eyesnpx skills add hoangsonww/Forge-Agentic-Coding-CLI --skill fresh-eyesgit clone --depth 1 https://github.com/hoangsonww/Forge-Agentic-Coding-CLIWrote 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/hoangsonww/forge-agentic-coding-cli/fresh-eyes)<a href="https://agentmods.dev/skills/hoangsonww/forge-agentic-coding-cli/fresh-eyes"><img src="https://agentmods.dev/badge/skills/hoangsonww/forge-agentic-coding-cli/fresh-eyes.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 | $0.00040 | $0.00271 |
| Opus 5 | $0.00020 | $0.00135 |
| Sonnet 5 | $0.00008 | $0.00054 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade A, and why
fresh-eyes 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 4d 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
/fresh-eyes — break the local minimum
When a session has accumulated too many assumptions, fresh eyes beat tired eyes. Context exhaustion can feel like convergence.
Prerequisite
Start a new Claude Code or Codex session. Don't just /clear.
Two-step prompt
Send, in order, the two prompts at
.flywheel/prompts/fresh-eyes.md:
- First, a deep context load (AGENTS.md + CLAUDE.md + FLYWHEEL.md + README.md + code investigation).
- Then, a review of
.beads/beads.jsonlagainst.flywheel/plans/<PLAN>.md.
When this operator pays off most
- Bead polishing flatlined after 3–4 rounds.
- Deep code review keeps finding the same class of bug.
- A major architectural decision feels locked in but nobody remembers justifying it.
After
If the fresh session finds new issues → back to /polish-beads.
If it comes back clean → you're genuinely at convergence. Proceed.
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.
- 4d ago First seen · 36 lines · 40 tokens per session scan A 8cca59481a9d
fresh-eyes is a skill published in the GitHub repository hoangsonww/Forge-Agentic-Coding-CLI (22 stars, last pushed 18d ago), licensed MIT. It adds 40 tokens to every session and 271 once invoked, about $0.0002 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 skills, from other repositories
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
hns-moaiadk-patterns
Skill "hns-moaiadk-patterns" from modu-ai/moai-adk, covering moai-adk-go domain patterns, architecture quick reference, key source paths, pipeline specialist delegation map and template-first build cycle.
moai-harness-learner
Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed.
hns-oss-docs-readme-sync
README 4-file synchronization procedure for the oss-docs harness: Korean README.ko.md as primary source, en/ja/zh derivation, the shared language-switcher header contract, section-order parity checklist, and the manual verification recipe (no linter exists for READMEs). Loaded by the content-author and…