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 Roshu18/bearstrike-ai --skill bug-huntinggit clone --depth 1 https://github.com/Roshu18/bearstrike-aiWrote 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/roshu18/bearstrike-ai/bug-hunting)<a href="https://agentmods.dev/skills/roshu18/bearstrike-ai/bug-hunting"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/bug-hunting/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/roshu18/bearstrike-ai/bug-hunting"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/bug-hunting.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 | $0.00016 | $0.00274 |
| Opus 5 | $0.00008 | $0.00137 |
| Sonnet 5 | $0.00003 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
bug-hunting 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 10d 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
bug-hunting
Use this flow for authorized bug bounty targets.
State machine
RECON -> ENUM -> VULN -> VERIFY -> REPORT
Rules
- Stay in scope at every step.
- Stop noisy scans when WAF is detected and switch to low-rate mode.
- Confirm findings manually before report generation.
Recommended sequence
- recon skill to map hosts and services.
- pentest-tools skill to choose matching tools per target type.
- exploitation skill only after strong signals.
- reporting skill to produce final markdown package.
Bug-hunt loop (efficient mode)
Use this loop to reduce noise and token burn:
- Build endpoint shortlist by business impact.
- Test authorization boundaries first.
- Validate one strong signal to completion.
- Expand only if evidence quality remains high.
Where bugs are often found
Focus checks on:
- ID fields in REST/JSON APIs
- GraphQL object queries and mutations
- Mobile/web API parity gaps
- Multi-step flows (cart -> payment -> refund)
- Export/report endpoints leaking cross-tenant data
Quality gate
Do not continue to next hypothesis until current one has:
- baseline response,
- altered request response,
- clear impact statement.
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.
- 10d ago First seen · 50 lines · 16 tokens per session scan A 212aefd47270
bug-hunting is a skill published in the GitHub repository Roshu18/bearstrike-ai (4 stars, last pushed 5mo ago), licensed MIT. It adds 16 tokens to every session and 274 once invoked, about $0.0001 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
triage
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
kicad-review
Design review and validation workflow for KiCAD projects via MCP tools. Triggers on: "review my design", "check for errors", "audit", "DRC", "ERC", "find problems", "design review", "is this ready", "validate", "check my schematic", "check my PCB", "what's wrong", "run checks", "pre-fab review".
blockrun-debug
Use when the BlockRun MCP server (@blockrun/mcp) is installed but misbehaving — 'Failed to connect', spawn npx ENOENT, blockrun missing from claude mcp list, HTTP 402 / Insufficient balance, fetch failed, video or music timeouts, a 501 'not served' error or 'API error after payment' while the balance never moved…
slow-query-optimize
Diagnose why a query is slow and propose a rewrite, using DeepSQL's plan analysis and AI query optimizer.
hmem-new-error
Create a new E-entry (bug/error) in hmem with the strict 5-level scaffold. Use when the user wants to log a bug, file a report, or document an error ('Bug loggen', 'log this error', 'Fehler eintragen'), or before any writememory with prefix='E'.
qa
QA test a live website with Axon discovery/content evidence plus browser automation when interaction is required. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.