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 HiAgencia/hi-claude --skill seeding-doubtsgit clone --depth 1 https://github.com/HiAgencia/hi-claudeWrote 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/hiagencia/hi-claude/seeding-doubts)<a href="https://agentmods.dev/skills/hiagencia/hi-claude/seeding-doubts"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/seeding-doubts/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/hiagencia/hi-claude/seeding-doubts"><img src="https://agentmods.dev/badge/skills/hiagencia/hi-claude/seeding-doubts.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 | $0.00137 | $0.00823 |
| Opus 5 | $0.00068 | $0.00411 |
| Sonnet 5 | $0.00027 | $0.00165 |
| Haiku 4.5 | $0.00014 | $0.00082 |
Grade A, and why
seeding-doubts 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seeding doubts (hi-claude)
There is no "it can't be done" — there is an angle not tried yet. This protocol manufactures the angle.
When it runs
- A quality stall: "something is wrong and I don't know what".
- Right after closing a big block, as an inverse pre-mortem: what did we NOT look at?
- Periodically, even when nothing looks wrong — especially then.
The five steps
-
Sequential introspection. Everything that caught your attention and was never chased: anomalies seen in passing, hunches, odd repeated numbers, doc↔code contradictions, things that "are surely fine". One thought = one doubt with its why. Forbidden to resolve: only formulate.
-
Seed three subagents with DISTINCT TONES. Each receives the seeds "under the speculation that something catches my eye", and its deliverable is MORE DOUBTS, never answers. Tones that work:
- the HOSTILE METHODOLOGIST — method, overfitting, baselines, what the sample cannot support
- the PARANOID AUDITOR — the data pipeline, "what if the cache photographed garbage?"
- the END USER — the product, what is missing, the honesty of the track record
Distinct tones matter more than more agents: three copies of the same lens find the same thing. They are read-only and what they bring is a hypothesis — verify it first-hand before acting.
-
Distil. Merge yours with theirs into one list ordered by damage×cost, in blocks: whatever touches what is ALREADY published or shipped comes first. Each item is a pending MEASUREMENT, never a conclusion. Persist them in
docs/ROADMAP.md. -
Validate the checkable ones IMMEDIATELY. Anything answerable with a real query, payload, or file gets verified on the spot. Confirmed → fix, with the evidence. Refuted → struck out WITH the datum that refuted it. A doubt refuted with data is worth as much as a confirmed one, and it stops the same doubt from coming back next month.
-
The rest becomes a measurement. Nothing is adopted or discarded without its method.
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 · 58 lines · 137 tokens per session scan A 2eb501f36d07
seeding-doubts is a skill published in the GitHub repository HiAgencia/hi-claude (2 stars, last pushed 21d ago), licensed MIT. It adds 137 tokens to every session and 823 once invoked, about $0.0007 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.