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 tosin2013/helmdeck --skill helmdeck-debuggit clone --depth 1 https://github.com/tosin2013/helmdeckWrote 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/tosin2013/helmdeck/helmdeck-debug)<a href="https://agentmods.dev/skills/tosin2013/helmdeck/helmdeck-debug"><img src="https://agentmods.dev/badge/skills/tosin2013/helmdeck/helmdeck-debug/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/tosin2013/helmdeck/helmdeck-debug"><img src="https://agentmods.dev/badge/skills/tosin2013/helmdeck/helmdeck-debug.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 | $0.00093 | $0.03207 |
| Opus 5.5 | $0.00037 | $0.01283 |
| Sonnet 5.5 | $0.00019 | $0.00641 |
| Haiku 4.5 | $0.00009 | $0.00321 |
Grade A, and why
helmdeck-debug 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.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the helmdeck integration debugger
When invoked, you run a diagnostic sweep across all helmdeck pipelines and capability packs, classify what you find, and produce a findings report with one ready-to-file GitHub issue per real bug. You draft issues — you do not file them until the maintainer says which to file.
Trigger this when a maintainer asks to debug / audit / health-check helmdeck, or
"find issues to file." For normal pack usage, that's the separate helmdeck
skill.
The bug classes you are hunting
These are the recurring, real classes (each has bitten this project). Look for all four:
- Oversold descriptions — a pipeline/pack
Descriptionpromises more than its steps actually do. Canonical example:builtin.grounded-blogonce said "fact-check + rewrite + publish" butcontent.groundonly cites claims (it does not rewrite voice/structure) andblog.publishsaves a markdown artifact by default (no Ghost credential → it does not publish anywhere). - Silent-bad-output inputs — an input that flows into user-visible output
without a guard, so a bad value produces bad output instead of an error.
Canonical example: a literal
{{TITLE}}once published a post titled{{TITLE}}. (The runner now rejects unfilled{{UPPER_SNAKE}}inputs inStartRun— verify that guard still covers every pipeline.) - Schema vs handler drift — a pack's declared
OutputSchemadoesn't match what its handler actually emits (key missing, or wrong type — e.g. declaringnumberfor a field the handler emits as an object). Handler-direct unit tests bypassEngine.Execute, soOutputSchema.Validatenever runs on them. - Failure misclassification — a pack returns a code-level error
(
handler_failed/internal/invalid_output) for what is really caller input.internal/pipelines/classify.gomaps those topack_bugand mints a prefilled issue URL — so a misclassified caller error files a bogus bug.
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 · 212 lines · 93 tokens per session scan A 05baf664b889
helmdeck-debug is a skill published in the GitHub repository tosin2013/helmdeck (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 3,207 once invoked, about $0.0004 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
xcodebuildmcp-cli
Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
triage
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
opik-explain
Root-cause a specific Opik trace, or a pattern across traces, and return a grounded explanation. Uses the hosted Opik MCP when it is connected, and falls back to SDK scripting otherwise. Returns the root cause, the evidence spans as clickable Opik UI links, and one suggested next step. Use for "why did this trace…
unicli-repair
Evidence-driven repair workflow for a broken Uni-CLI adapter. Trigger on a failed unicli envelope, a quarantined adapter, or an explicit adapter-repair request. Classifies non-source failures, edits only the reported adapter path, and uses the original command as a bounded oracle.
maintenance
Investigate, adopt, and verify dependency updates. Captures what changed, understands why, cross-references against the codebase, and runs final checks. Supports two entry modes: run the full flow end-to-end, or review updates you already applied.