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 deepaksinghcs14/deadeye-cc --skill deadeye-debtgit clone --depth 1 https://github.com/deepaksinghcs14/deadeye-ccWrote 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/deepaksinghcs14/deadeye-cc/deadeye-debt)<a href="https://agentmods.dev/skills/deepaksinghcs14/deadeye-cc/deadeye-debt"><img src="https://agentmods.dev/badge/skills/deepaksinghcs14/deadeye-cc/deadeye-debt/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/deepaksinghcs14/deadeye-cc/deadeye-debt"><img src="https://agentmods.dev/badge/skills/deepaksinghcs14/deadeye-cc/deadeye-debt.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 | $0.00000 | $0.00580 |
| Opus 5 | $0.00000 | $0.00290 |
| Sonnet 5 | $0.00000 | $0.00116 |
| Haiku 4.5 | $0.00000 | $0.00058 |
Grade A, and why
deadeye-debt 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deadeye Debt
Coder mode marks deliberate simplifications with a pinned grammar — the
literal ceiling: and upgrade: keywords are required so this ledger
can parse them reliably:
# deadeye: <shortcut>. ceiling: <limit>. upgrade: <trigger>.
e.g. # deadeye: global lock. ceiling: single-writer throughput. upgrade: per-account locks when contention shows.
This skill collects them into a ledger. Older freeform markers (no
ceiling:/upgrade: keywords) still count — parse them best-effort.
How
Run:
grep -rnE '(#|//|/\*|<!--) ?deadeye:' . \
--exclude-dir=node_modules --exclude-dir=.git \
--exclude-dir=dist --exclude-dir=build --exclude-dir=vendor
Filter before counting — three kinds of hit are not markers, verify each one before it lands in the ledger:
- This skill's own file (
skills/deadeye-debt/SKILL.md) — its own grammar example matches its own grep. - A line quoting the grammar template verbatim, with the literal
placeholders
<shortcut>,<limit>, or<trigger>still in it — docs and other skills quote the sentence to explain the convention; a real marker always has those filled in with actual text, never the bracketed words themselves. - Non-code brand/marketing copy (an SVG comment, a README aside) that happens to start with "deadeye:" but isn't a shortcut-marker comment at all — read the hit, don't just count it.
Only what survives that filter is a real marker.
Ledger format
One row per marker:
<file>:<line> — <what was simplified>. ceiling: <limit>. upgrade: <trigger>.
A marker whose comment names no upgrade condition gets tagged
no-trigger — those are the ones most likely to rot.
For ownership questions, suggest git blame -L<line>,<line> <file>.
More than ~30 markers: group rows by directory and report per-group counts plus the worst offenders, still ending with the exact total.
End with: <N> markers, <M> with no trigger. — or, if the grep finds
nothing: No deadeye: debt. Clean ledger.
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 Changed · +16 lines 9a26d5b7f796
- 10d ago First seen · 52 lines · 0 tokens per session scan A 07fa0e9f2808
deadeye-debt is a skill published in the GitHub repository deepaksinghcs14/deadeye-cc (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 580 tokens. 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
gemini
Cross-model second opinion from Google Gemini — a different AI reviewing the same changes, with deep Google ecosystem knowledge. Three modes: review (pass/fail gate for Google Ads campaigns, SEO metadata, or code), challenge (adversarial stress-test that tries to break your changes), and consult (open Q&A with Gemini…
critical-code-reviewer
Rigorously review code or pull requests for correctness, security, accessibility, maintainability, tests, and edge cases. Use when users request a critical code review, want a guided walkthrough of findings, need implementer-facing feedback, or want to prepare, create, or submit a GitHub pull request review.
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
codex-ab
Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.