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 fledgeling-co/fledgeling-plugins --skill better-goalgit clone --depth 1 https://github.com/fledgeling-co/fledgeling-pluginsWrote 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/fledgeling-co/fledgeling-plugins/better-goal)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/better-goal"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/better-goal/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/fledgeling-co/fledgeling-plugins/better-goal"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/better-goal.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 | $0.00361 | $0.04063 |
| Opus 5 | $0.00180 | $0.02031 |
| Sonnet 5 | $0.00072 | $0.00813 |
| Haiku 4.5 | $0.00036 | $0.00406 |
Grade A, and why
better-goal 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 yesterday.
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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
better-goal — a finish line that verifies itself
A long run needs three things the model cannot supply about itself: something that decides whether the work is done, something that notices when the run has died, and a record that answers "how's it going" without interrupting it. This skill builds all three out of command hooks, a monitor, and a file.
Two of those live inside the session, so a third has to live outside it. A Stop
hook cannot fire for a turn that ended on an API error, and a Monitor dies with
the session that armed it — which is how one run sat at armed: true on turn 17
for fourteen days with nobody told. arm.sh therefore registers four events, not
one: Stop runs the gates, StopFailure and SessionEnd record the deaths the
guard never sees, and SessionStart reports what is still armed to the next
session that opens the repo.
It does not use /goal. That command registers a prompt Stop hook whose verdict
comes from a small model reading the transcript — so it is judged on what the
run said, it cannot run a command, and Claude Code overrides any Stop hook
after 8 consecutive blocks while reporting the turn as completed. The guard
here replaces the evaluator with exit codes and raises that cap deliberately.
references/mechanics.md carries the evidence for each of those claims.
Deliver the harness. The armed run does the underlying work, so do not start it in this pass. Make routine judgment calls yourself and check in only where two readings would produce materially different gates.
references/failure-modes.md maps each observed failure to its fix.
references/gate-craft.md is how to turn "done" into commands.
references/presets.md carries the two recipes people ask for most.
Running as a Gemini model? Read gemini.md in this directory first, then follow this file with the overrides it names. It turns the finish line into a counted worklist, requires every gate to be proved able to fail before arming, and makes you read the state file and hook registration back off disk before reporting the run as armed. Other models skip it.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- gemini.md 16 KB
- references/failure-modes.md 14 KB
- references/gate-craft.md 6.9 KB
- references/mechanics.md 13 KB
- references/presets.md 4.1 KB
- references/templates.md 6.8 KB
- scripts/arm.sh 9.1 KB runs code
- scripts/disarm.sh 4.5 KB runs code
- scripts/guard.sh 16 KB runs code
- scripts/preflight.sh 8.4 KB runs code
- scripts/sentinel.sh 5.2 KB runs code
- scripts/status.sh 3.8 KB runs code
- scripts/watch.sh 8.3 KB runs code
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.
- yesterday Changed · -2 lines · +4 tokens per session ad789934aedb
- 9d ago First seen · 278 lines · 357 tokens per session scan A 425440803038
better-goal is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 361 tokens to every session and 4,063 once invoked, about $0.0018 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…