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/maximumsoft-co-ltd/claude-flightdeck/flightdeck-feedbacknpx skills add Maximumsoft-Co-LTD/claude-flightdeck --skill flightdeck-feedbackgit clone --depth 1 https://github.com/Maximumsoft-Co-LTD/claude-flightdeckWrote 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/maximumsoft-co-ltd/claude-flightdeck/flightdeck-feedback)<a href="https://agentmods.dev/skills/maximumsoft-co-ltd/claude-flightdeck/flightdeck-feedback"><img src="https://agentmods.dev/badge/skills/maximumsoft-co-ltd/claude-flightdeck/flightdeck-feedback.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 | $0.00115 | $0.01799 |
| Opus 5 | $0.00057 | $0.00899 |
| Sonnet 5 | $0.00023 | $0.00360 |
| Haiku 4.5 | $0.00012 | $0.00180 |
Grade A, and why
flightdeck-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 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/flightdeck-feedback — Send feedback upstream
Open a structured issue against the canonical claude-flightdeck template repo — a template bug, a rule that misfired, a preset you want, a broken skill, or onboarding friction.
This is PULL feedback — it only runs when you invoke it, and always shows a preview before sending. It never sends anything automatically.
Token budget (MANDATORY)
- One-shot: ~5-10k tokens total. No passive cost — the skill does nothing unless invoked. There is no hook, no background poll.
- Read
.ai-workflows/manifest.jsononce (small — version + commit + presets + placeholders). - Read
docs/project/retros/onboarding.mdwithlimit: 100only foronboarding-type feedback — skip it for every other type. - Do NOT scan the codebase or Read large files. Feedback is about the template, not the user's project. If you find yourself grepping source, you're off-track.
Invocation
| Form | Effect |
|---|---|
/flightdeck-feedback |
Interactive — asks the feedback type first |
/flightdeck-feedback bug |
Skip the type question — template bug |
/flightdeck-feedback rule |
Skip — a rule misfired / is wrong |
/flightdeck-feedback preset |
Skip — request a new preset |
/flightdeck-feedback skill |
Skip — a skill is broken / unclear |
/flightdeck-feedback onboarding |
Skip — onboarding wizard feedback |
/flightdeck-feedback --url-only |
Don't use gh; print a prefilled issue URL to click |
Canonical repo
Feedback routes to Maximumsoft-Co-LTD/claude-flightdeck (hardcoded
below). See ## For org-forks if your team forked it.
Steps
- Read manifest. Read
.ai-workflows/manifest.json→ extractversion,source_commit,presets,profile. If the file is missing, note "not installed via flightdeck — version unknown" and continue with empty values (still useful feedback). - Determine feedback type. From the subcommand arg, or — if none —
AskUserQuestionwith the 5 types below. Map each to its issue-form name + label:
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 · 136 lines · 115 tokens per session scan A c6709ee54d95
flightdeck-feedback is a skill published in the GitHub repository Maximumsoft-Co-LTD/claude-flightdeck (2 stars, last pushed 2mo ago), licensed MIT. It adds 115 tokens to every session and 1,799 once invoked, about $0.0006 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
vc-agent-strategy-compare
Evaluate 4 execution strategies (sequential, parallel-subagents, workflow, agent-team) for a phase or fan-out task. Outputs 7-signal score table, agent count math, cost guards, and strategy recommendation.
vc-generate-phase-program
Generate kickoff artifacts for a multi-phase program: umbrella plan, Program Goal Charter, session-goal block, per-phase plan stubs, and the 7-step per-phase inner loop reference.
vc-intent-clarify
Clarify intent before RIPER-5 phase delegation. Scores ambiguity (4 signals); generates structured multi-choice questions for Tier 2. Two-mode: SIMPLE and DEEP.
vc-autoresearch
Loop: find gaps → fix → repeat until agents find no gaps or a metric goal is hit. Shared loop primitive for PVL, EVL, and standalone quality runs.
vc-generate-closeout
Generate the post-EXECUTE closeout packet for a plan or phase. Includes archive-readiness classification, drift signal scoring, commit checkpoint recommendation, and move-on next-state recommendation.
vc-validate-findings
Use when running VALIDATE V2-V3 fan-out. Two-layer investigation (4 dimension agents + per-section feasibility agents) synthesized into PASS/CONDITIONAL/BLOCKED net gate. Strategy-agnostic.