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 decision-briefgit 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/decision-brief)<a href="https://agentmods.dev/skills/fledgeling-co/fledgeling-plugins/decision-brief"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/decision-brief/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/decision-brief"><img src="https://agentmods.dev/badge/skills/fledgeling-co/fledgeling-plugins/decision-brief.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 | $0.00051 | $0.00632 |
| Opus 5.5 | $0.00020 | $0.00253 |
| Sonnet 5.5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
decision-brief 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 5d 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
Research to decision
Read the evidence contract. Start with the choice to make, the user's constraints and what would change the answer. Reuse prior research with its dates and source identities. A historical comparison identifies candidates, not today's prices or compatibility. Preserve the requested product and task; do not turn a narrow choice into a market survey.
Separate hard constraints from preferences: exact platform/version, workload,
capacity, compatibility, budget, region, ongoing costs, delivery time and risk.
Resolve discoverable facts yourself. Use clarify:clarify only for a material
user-owned constraint. Include the keep-current/do-nothing option if viable;
do not manufacture a purchase requirement.
Research only gaps that can change the decision. Verify unstable prices, availability, specifications and supported versions at current sources. Prefer manufacturer documentation for compatibility and specifications and independent measured tests for performance claims. Record exact SKU/configuration, test workload, software version and date. Syndicated summaries of one benchmark are one source, not independent corroboration. Separate facts, calculated estimates and inference; conflicts remain visible. Stop when a feasible recommendation is supported and remaining uncertainty would not change it, or name the missing measurement that prevents choosing. Do not keep browsing until every possible product has been ranked.
Storage decisions need actual access paths: local SSD, network share, platform library support and network speed may be different constraints. Separate usable capacity, redundancy and backup; verify whether games/apps can run or only be stored on the proposed path. Computing comparisons use the target workload, thermals, sustained performance and total cost rather than headline chip names. Testing tools use observable coverage, supported target/runtime, CI/foreground requirements, evidence export and recurring cost; a demo screenshot is not proof the tool can observe the needed effect. A safe read-only compatibility probe can proceed; installing software, starting paid trials or changing environments needs applicable authority.
Deliver a compact comparison and a verdict: recommended option, why it satisfies
the constraints, cost with check time/currency, weaknesses, uncertainty and the
condition that would change the answer. If evidence cannot settle it, propose
one discriminating test with a success criterion. Route a requested published
research page to dossier-report:dossier-report only after confirming its
publishing and paid-research scope; a decision brief does not grant that scope.
The recommendation ends the research phase. Buying, starting subscriptions,
provisioning infrastructure or publishing requires separate applicable authority.
If retaining decisions, use the ledger format
with domain decision, and retain superseded conclusions with their reason so a
new run improves the same decision instead of reopening it from scratch.
What ships with it
1 file 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.
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.
- 5d ago First seen · 54 lines · 51 tokens per session scan A fb9e0a8ee17d
decision-brief is a skill published in the GitHub repository fledgeling-co/fledgeling-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 51 tokens to every session and 632 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-12.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…