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 planninggit 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/planning)<a href="https://agentmods.dev/skills/roshu18/bearstrike-ai/planning"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/planning/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/planning"><img src="https://agentmods.dev/badge/skills/roshu18/bearstrike-ai/planning.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 | $0.00511 |
| Opus 5 | $0.00008 | $0.00255 |
| Sonnet 5 | $0.00003 | $0.00102 |
| Haiku 4.5 | $0.00002 | $0.00051 |
Grade A, and why
planning 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 8d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
planning
Objective
Create a clear, low-noise attack plan before any active testing.
Mandatory pre-checks
- Read research-notes for current high-signal bug classes.
- Use traffic-proxy skill only after a concrete workflow hypothesis exists.
- Scope validation
- Confirm in-scope domains/IPs.
- Confirm out-of-scope exclusions.
- Risk tiering
- Public internet production targets: low-noise only first.
- Internal labs/CTF: broader active scans allowed.
- Initial target profile
- Domain, ASN, technology hints, auth surface, likely API presence.
Priority scoring model
Score each task by impact x confidence x feasibility (1-5 each).
- High score (60+): execute first.
- Medium (30-59): execute after first evidence.
- Low (<30): defer.
Output contract before scanning
Produce TODO list with:
- Phase: recon / enum / vuln / verify / report
- Tool: exact tool name
- Purpose: one sentence
- Success signal: what output means progress
- Stop condition: when to stop this task
Example TODO item
- Phase: recon
- Tool: subfinder
- Purpose: collect passive subdomains for attack surface
- Success signal: non-empty unique subdomain set
- Stop condition: duplicate-only output in 2 consecutive runs
Execution rule
Never run exploitation until at least one strong vulnerability signal is confirmed in recon/enum.
2024-2026 high-signal focus
Prioritize bug classes that repeatedly show high bounty impact:
- Broken access control (IDOR/BOLA/role boundary failures)
- Authentication/session logic flaws
- API data exposure and object-level authorization issues
- Misconfiguration and sensitive endpoint exposure
Endpoint-first planning
Before heavy scans, build a shortlist of high-value endpoint clusters:
- Account and profile endpoints
- Payment and transaction workflows
- Admin and internal API routes
- File upload and export/import endpoints
For each cluster, define:
- Expected actor (anonymous/user/admin/service)
- Expected object boundary (self-only/team/global)
- One negative test case (forbidden access)
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.
- 8d ago First seen · 82 lines · 16 tokens per session scan A 84f14cdda158
planning 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 511 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
surf
Use when the user wants crypto data — token prices, on-chain SQL, prediction-market positions, CEX order books, wallet labels/net-worth, social mindshare, news, or unified search. 83 endpoints across exchange, on-chain, wallet, social, prediction, news and search — one API, flat $0.0085/call in USDC via x402. Settles…
gentech-blockrun
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent. Covers daily usage patterns, cost-optimized workflows, multi-tool pipelines, and reliable error handling for BlockRun's full toolset.
portainer-mcp-hygiene
How to drive the Portainer MCP server's tools correctly — both reading and mutating. Reading: project responses with select (JMESPath), where the heavy fields live (snapshots, status blocks, managed fields), how to handle non-JSON Docker/K8s proxy endpoints (container and pod logs, stats, exec), and how to interpret…
vault-for-llm
Connect OpenClaw to Vault Agent Memory as a local-first governed project memory layer. Search first, then bounded-read cited source ranges; propose new memories as candidates instead of writing directly into active memory.
setup
Configure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables, unapproved environment variables, unavailable Qdrant tools, "Failed to connect" errors, and setup requests.
kicad-library
Library management workflow for KiCAD — creating symbols, footprints, and managing libraries via MCP tools. Triggers on: "create a symbol", "make a footprint", "custom component", "register library", "find a part", "pin numbering", "new symbol", "new footprint", "add to library", "library path", "pad layout".