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 ashutoshsinghpr7/wikiskill --skill search-miss-binarygit clone --depth 1 https://github.com/ashutoshsinghpr7/wikiskillWrote 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/ashutoshsinghpr7/wikiskill/search-miss-binary)<a href="https://agentmods.dev/skills/ashutoshsinghpr7/wikiskill/search-miss-binary"><img src="https://agentmods.dev/badge/skills/ashutoshsinghpr7/wikiskill/search-miss-binary.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00330 |
| Opus 5 | $0.00018 | $0.00165 |
| Sonnet 5 | $0.00007 | $0.00066 |
| Haiku 4.5 | $0.00004 | $0.00033 |
Grade A, and why
search-miss-binary 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 2d 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
Search Can Silently Miss Binary-Detected Files
Problem
search_files (ripgrep) returned 0 matches for SECRET- even though
data.log contains SECRET-1722. Trusting the empty result would fail the
task ("which file contains the secret?").
Root cause
Ripgrep skips files it heuristically classifies as binary. The empty result means "no match in text-classified files", not "string absent".
Fix
- When a content search returns nothing but files exist, do NOT trust the empty result blindly.
- Force text mode:
grep -a -l PATTERN <files>and/orfile+xxd/hexdump to confirm where the string lives. - Confirm the actual match content before writing the answer.
Evidence
- Hit in a real graded task:
SECRET-1722lived in a binary-detected file; the agent correctly suspected "encoding or binary detection issues" and verified directly instead of concluding "not found".
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.
- 2d ago First seen · 39 lines · 36 tokens per session scan A caa784b6ea00
search-miss-binary is a skill published in the GitHub repository ashutoshsinghpr7/wikiskill (117 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 330 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
harness-optimizer
Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.
debug-and-fix
Strategies for debugging build failures, runtime errors, writing complete output files (ICS/JSON/config), and constraint satisfaction tasks.
systematic-exploration
Strategies for avoiding dead ends and premature conclusions. Read this when stuck or when an approach seems to not work.
longstrider
Longstrider is the optimization spell for systems that already work. It makes the path shorter without changing the destination. It cares about sustained pace, not flashy one-off benchmarks.
mage-hand
Use this skill for small, careful remote manipulations where dexterity matters more than force.
blindness-deafness
In D&D, Blindness/Deafness selectively removes one sense — the target can still act but loses critical awareness. The real-world version is selective channel muting: blocking a process from seeing certain inputs (input filtering, API response redaction), deafening it to specific signals (suppressing webhooks, ignoring…