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 tomzx/agents --skill synthesize-feedbackgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/synthesize-feedback)<a href="https://agentmods.dev/skills/tomzx/agents/synthesize-feedback"><img src="https://agentmods.dev/badge/skills/tomzx/agents/synthesize-feedback/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/tomzx/agents/synthesize-feedback"><img src="https://agentmods.dev/badge/skills/tomzx/agents/synthesize-feedback.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 | $0.00044 | $0.00592 |
| Opus 5 | $0.00022 | $0.00296 |
| Sonnet 5 | $0.00009 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
synthesize-feedback 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 6d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Synthesize Feedback
Combines the quantitative health report with qualitative signal from support tickets, sales conversations, NPS, reviews, and usage observations. The output (feedback-loop.md) is what the Measure gate reads to decide double-down / iterate / sunset, and it feeds back into Discover to close the PDLC loop.
Prerequisites
- Apply the shared PDLC conventions in
skills/pdlc/references/shared.md. health-report.mdfromreview-metrics, plus available qualitative sources.
Steps
- Gather qualitative signal across channels: support tickets, sales/CS notes, NPS verbatims, reviews, in-product feedback. Time-box the window to match the health report.
- Code the feedback into themes, each with a frequency and a severity. Separate "the thing doesn't work" (defects) from "the thing isn't valuable" (problem-fit).
- Cross-reference with the health report: does the qualitative story agree with the numbers? Where they disagree, that disagreement is itself a finding.
- Identify the highest-leverage next problem to solve (the candidate input to the next Discover cycle).
- Recommend the gate verdict:
double-down(scale what works),iterate(tune based on feedback), orsunset(the value isn't there). - Write
feedback-loop.mdto the initiative directory.
Output Format
Use the template at skills/pdlc/templates/initiatives/feedback-loop.md.
Outcome
If $OUTCOME_YAML is set:
| Verdict | When |
|---|---|
double-down |
Strong value confirmed; scale it |
iterate |
Real value, needs tuning; loop back to Discover |
sunset |
Value not materializing; run sunset-product |
Completion Checklist
- Feedback themed with frequency and severity
- Defects separated from problem-fit issues
- Qualitative story cross-referenced with the health report
- Highest-leverage next problem identified
- Gate recommendation stated with rationale
Next Step
Run the Measure gate via make-decision (verdict vocabulary: double-down / iterate / sunset).
iterate→ the loop closes: return todiscover-problemswithfeedback-loop.mdas input.sunset→ loadsunset-product.double-down→ loadbuild-roadmapto scale, or capture learnings and close.
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.
- 6d ago First seen · 53 lines · 44 tokens per session scan A d837165ba119
synthesize-feedback is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed yesterday), licensed MIT. It adds 44 tokens to every session and 592 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 2026-09-03.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.