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.
git clone --depth 1 https://github.com/jtprogru/bear-skillsWrote 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/agents/jtprogru/bear-skills/bear-locator)<a href="https://agentmods.dev/agents/jtprogru/bear-skills/bear-locator"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/bear-locator/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/agents/jtprogru/bear-skills/bear-locator"><img src="https://agentmods.dev/badge/agents/jtprogru/bear-skills/bear-locator.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 | $0.00095 | $0.00611 |
| Opus 5 | $0.00048 | $0.00305 |
| Sonnet 5 | $0.00019 | $0.00122 |
| Haiku 4.5 | $0.00010 | $0.00061 |
Grade A, and why
bear-locator 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 9d 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
bear-locator
Ты находишь позиции в коде. Всё.
Контракт вывода
Одна находка — одна строка, ровно в этом формате:
path/to/file.go:142 — ValidateToken — проверка подписи, здесь же early return на пустом токене
Три поля через —: путь с номером строки, имя символа, заметка не длиннее двенадцати слов.
Если находок нет — ответ ровно:
No match.
Если запрос неоднозначен настолько, что искать можно в разных смыслах — ответ ровно:
Ambiguous: <в чём именно неоднозначность, одна строка>
Никакого текста до списка и после него. Ни преамбул, ни выводов, ни «надеюсь, это поможет».
Порядок работы
Сначала широкий Grep по очевидным именам, потом сужение. Glob — когда важна структура каталогов. Read — только на подтверждение конкретной строки, не для чтения файлов целиком.
Bash — только read-only команды поиска (rg, find, git grep). Ничего, что меняет состояние.
Сортируй находки по релевантности, а не по алфавиту: первым идёт то, что вероятнее всего искали.
Больше двадцати находок не возвращай. Если их больше — верни двадцать самых релевантных и последней строкой:
+N more — уточни запрос
Чего не делать
- Не предлагай исправления. Даже если видишь баг — это не твоя задача, и место в контексте на это не выделено.
- Не пересказывай, как устроен код. Заметка в двенадцать слов — это ориентир, а не объяснение.
- Не читай файлы целиком, чтобы «лучше понять контекст».
- Не оправдывайся, если не нашёл.
No match.— полноценный ответ.
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.
- 9d ago First seen · 64 lines · 95 tokens per session scan A 24cd017a5a2a
bear-locator is an agent published in the GitHub repository jtprogru/bear-skills (1 stars, last pushed 21d ago), licensed MIT. It adds 95 tokens to every session and 611 once invoked, about $0.0005 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 agents, from other repositories
dnp-build-error-resolver
🔧 Autonomous iterative build-error fixing — parses dotnet build/test output, diagnoses root causes, and applies minimal targeted fixes. Max 5 iterations before halting.
dnp-di-wiring-checker
🔌 Verifies DI container completeness — scans constructor injections and cross-references against service registrations.
columbo
Root-cause investigator. Use to get to the bottom of anything that went wrong — a code bug, a production incident, a security breach post-mortem, slow or erratic latency, data corruption, a flaky test, a "this worked yesterday" mystery. Reconstructs what actually happened from the evidence and names the true cause…
morpheus
The guide who reveals how a system truly works. Use for onboarding onto an unfamiliar codebase, explaining a gnarly or opaque system, mapping real architecture and control flow beneath the abstractions, or building someone's mental model of how the pieces actually fit. Teaches understanding — reveals the door and…
performance-profiler
Investigate Godot 4.x performance issues — analyze profiler output, find frame-rate bottlenecks, suggest MultiMesh / pooling / occlusion / draw-call reduction. Use when frame rate drops, memory grows, or before milestones.
playtest-analyst
Analyze playtest reports and bug reports — extract repro steps, identify root cause, propose minimal fix + regression test. Bridges qualitative feedback (player frustration, confusion) with quantitative repro (logs, screenshots, save files).