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 bleedmode/dearuser --skill dearuser-feedbackgit clone --depth 1 https://github.com/bleedmode/dearuserWrote 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/bleedmode/dearuser/dearuser-feedback)<a href="https://agentmods.dev/skills/bleedmode/dearuser/dearuser-feedback"><img src="https://agentmods.dev/badge/skills/bleedmode/dearuser/dearuser-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/bleedmode/dearuser/dearuser-feedback"><img src="https://agentmods.dev/badge/skills/bleedmode/dearuser/dearuser-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 | $0.00028 | $0.00515 |
| Opus 5.5 | $0.00011 | $0.00206 |
| Sonnet 5.5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
dearuser:feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Dear User — Feedback
Send the user's message to the Dear User founder inbox.
What to do
- Take whatever the user said (or the argument text) and pass it verbatim as
message. Do NOT rewrite, shorten, or summarise. - Try calling
mcp__dearuser__feedbackwith{ "message": "<the user's text>" }. - If the tool is not available (first turn of session — MCP tools load lazily), use this Bash fallback. Pipe the message via stdin so apostrophes, quotes, and newlines in the user's text don't break shell quoting:
jq -Rn --arg msg "$(cat <<'END_OF_DU_MSG'
<the user's text — verbatim, any content, no escaping> END_OF_DU_MSG )" '{message:$msg}' | npx -y -p @poisedhq/dearuser-mcp dearuser-run feedback -
The `<<'END_OF_DU_MSG'` (quoted heredoc marker) prevents bash from interpreting any character in the message — apostrophes, `$`, backticks, backslashes all pass through literally. `jq` then produces safe JSON and pipes it to `dearuser-run -` which reads from stdin.
If the command prints to stderr or exits non-zero, show that output to the user — the message was NOT sent.
4. Show the returned confirmation to the user exactly as returned — it's already short and friendly.
## Optional parameters
Only include these when the user explicitly provided them:
- `rating` (1–5) — only when the user typed a number
- `context` — `collab` / `security` / `health` / `wrapped` / `general`. Default to the tool they just ran, or `general`.
- `opt_in_followup` + `email` — only when the user explicitly asked for a reply
## Rules
- Write-only. This is the one place Dear User sends data out. Never invoke it without an explicit user message.
- Never infer sentiment to fill in `rating`. Leave it out unless the user said a number.
- If the tool returns an error, show the error text — the message was NOT sent.
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.
- 1mo ago First seen · 38 lines · 28 tokens per session scan A 2103455309c1
dearuser:feedback is a skill published in the GitHub repository bleedmode/dearuser (0 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 515 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
utility-mermaid-diagrams
Teaches PMs to create syntactically valid mermaid diagrams by selecting the right diagram type for their communication need, following syntax validity rules, and validating before shipping. Covers all 15 mermaid diagram types with PM-relevant examples and a dual-lens navigation system.
utility-pm-critic
Run adversarial review on a PM artifact via the pm-critic sub-agent. Returns findings graded P0/P1/P2/P3 with a concrete fix suggestion per finding and a machine-readable status block. Use after producing a PRD, meeting recap, OKR set, persona, or any PM artifact you want stress-tested before it ships.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
utility-pm-skill-auditor
Run a repo-wide cross-cutting governance audit via the pm-skill-auditor sub-agent. Aggregates the enforcing validator suite, re-derives aggregate counters, and surfaces cross-cutting issues no single validator catches, graded P0/P1/P2/P3 with a machine-readable status. Use for pre-release readiness checks or a…
develop-solution-brief
Creates a concise one-page solution overview that communicates the proposed approach, key decisions, and trade-offs. Use when pitching solutions to stakeholders, aligning teams on approach, or documenting solution intent before detailed specification.
develop-spike-summary
Documents the results of a completed technical or design spike, capturing the original question, approach, evidence-backed findings, and a clear proceed-or-not recommendation so the team does not re-litigate the exploration. Use once a time-boxed investigation has concluded. For the architecture decision the spike…