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 nthnclrk/enablement-skills --skill field-feedback-synthesizergit clone --depth 1 https://github.com/nthnclrk/enablement-skillsWrote 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/nthnclrk/enablement-skills/field-feedback-synthesizer)<a href="https://agentmods.dev/skills/nthnclrk/enablement-skills/field-feedback-synthesizer"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/field-feedback-synthesizer/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/nthnclrk/enablement-skills/field-feedback-synthesizer"><img src="https://agentmods.dev/badge/skills/nthnclrk/enablement-skills/field-feedback-synthesizer.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 | $0.00104 | $0.00922 |
| Opus 5 | $0.00052 | $0.00461 |
| Sonnet 5 | $0.00021 | $0.00184 |
| Haiku 4.5 | $0.00010 | $0.00092 |
Grade A, and why
field-feedback-synthesizer 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Field feedback synthesizer
Turn a defined feedback corpus into findings a decision owner can use. Score source breadth before you recommend. Observation is what the sources said. Recommendation is what someone should do next. Keep them apart.
Fails. "The field is telling us the security FAQ is broken. Rewrite it this week."
Passes. "17 mentions of security-review friction across 9 independent accounts and 3 source types. Observation: sellers cannot find or cannot use the current FAQ. Recommendation: confirm discoverability before rewriting. Confidence: medium — no usage denominator, and 8 of 17 mentions came from one Slack channel."
Asset-demand scoring is content-gap-analysis. Recurring call objections are call-insights-to-objections. Why deals closed is win-loss-synthesis. One recorded call is call-review-coach.
Confirm Inputs First
Ask only for the inputs that change the synthesis:
- The decision or research question
- Included sources, timeframe, teams, segments, and exclusions
- Counting unit and denominator: records, respondents, accounts, opportunities, or calls
- Confidentiality and quotation boundaries
If the corpus, counting unit, or question is unresolved, return an analysis plan rather than quantified findings. Do not invent usage, win rates, or quotes.
Read The Right Reference
Read references/feedback-coding-framework.md before you code the corpus, score breadth, or write a recommendation. Skip it if the user already coded the set and wants implications from a finished register.
Default Workflow
- Frame the sample. Question, inclusion rules, collection method, counting unit, denominator, and known bias. Done when a reviewer can see what this corpus can and cannot represent.
- Register sources. Stable record and origin IDs. Collapse copies of the same originating statement. Keep independent observations separate.
- Calibrate the codebook. Pilot on a mixed subset. Resolve overlapping codes. Freeze before the full pass, or record every later change.
- Code without collapsing layers. Theme, segment, stage, evidence type, and severity. Frequency, severity, evidence strength, and business impact stay separate dimensions.
- Quantify with the right denominator.
Show
n/N, base sizes, and independent-source breadth. A convenience sample is not population prevalence. - Score breadth, then confidence. Independent units, source types, segments, and time periods. High frequency from one biased channel is not high confidence.
- Look for what a ranking would hide. Minority, role-specific, regional, and contradictory signals. Report a cut only when the base supports it.
- Interpret, then recommend. Observation, interpretation, root-cause hypothesis, and decision are four lines. Each material recommendation needs an owner, a validation step, and what would disconfirm it.
What ships with it
2 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.
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 · 75 lines · 104 tokens per session scan A 8994ed7de852
field-feedback-synthesizer is a skill published in the GitHub repository nthnclrk/enablement-skills (13 stars, last pushed 22d ago), licensed MIT. It adds 104 tokens to every session and 922 once invoked, about $0.0005 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
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…