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 bish-x/bx-dev-skill --skill bx-devgit clone --depth 1 https://github.com/bish-x/bx-dev-skillWrote 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/bish-x/bx-dev-skill/bx-dev)<a href="https://agentmods.dev/skills/bish-x/bx-dev-skill/bx-dev"><img src="https://agentmods.dev/badge/skills/bish-x/bx-dev-skill/bx-dev/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/bish-x/bx-dev-skill/bx-dev"><img src="https://agentmods.dev/badge/skills/bish-x/bx-dev-skill/bx-dev.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 | $0.00057 | $0.26270 |
| Opus 5.5 | $0.00023 | $0.10508 |
| Sonnet 5.5 | $0.00011 | $0.05254 |
| Haiku 4.5 | $0.00006 | $0.02627 |
Grade B, and why
bx-dev scanned grade B with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Never tell the user "still waiting on Dev" after a final `subagent_notification` has already arrived. Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- API / CLI / no interface -> test via shell commands (curl, running commands) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
echo "$changed_files" | grep -iE '(auth|login|session|cookie|token|password|secret|credential|jwt|oauth|csrf|sanitiz|encrypt|decrypt|sql.?injection|migration|\.env|deserializ|exec|eval|child_process|webhook)' The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- docs/CODEX-ORCHESTRATION.md 8.1 KB
- docs/MERGE-PROTOCOL.md 35 KB
- skill-library/architecture/ddd/SKILL.md 53 KB
- skill-library/architecture/INDEX.md 1.1 KB
- skill-library/backend/ai-security/references/atlas-coverage.md 8.8 KB
- skill-library/backend/ai-security/SKILL.md 17 KB
- skill-library/backend/cloud-security/references/cspm-checks.md 8.7 KB
- skill-library/backend/cloud-security/SKILL.md 16 KB
- skill-library/backend/dependency-auditor/references/dependency_management_best_practices.md 18 KB
- skill-library/backend/dependency-auditor/references/license_compatibility_matrix.md 8.7 KB
- skill-library/backend/dependency-auditor/references/vulnerability_assessment_guide.md 14 KB
- skill-library/backend/dependency-auditor/SKILL.md 13 KB
- skill-library/backend/docker-development/references/compose-patterns.md 5.7 KB
- skill-library/backend/docker-development/references/dockerfile-best-practices.md 5.1 KB
- skill-library/backend/docker-development/SKILL.md 11 KB
- skill-library/backend/INDEX.md 5.1 KB
- skill-library/backend/kubernetes-specialist/SKILL.md 7.3 KB
- skill-library/backend/mcp-builder/LICENSE.txt 11 KB
- skill-library/backend/mcp-builder/reference/evaluation.md 21 KB
- skill-library/backend/mcp-builder/reference/mcp_best_practices.md 7.2 KB
- skill-library/backend/mcp-builder/reference/node_mcp_server.md 28 KB
- skill-library/backend/mcp-builder/reference/python_mcp_server.md 25 KB
- skill-library/backend/mcp-builder/scripts/connections.py 4.8 KB runs code
- skill-library/backend/mcp-builder/scripts/evaluation.py 12 KB runs code
- skill-library/backend/mcp-builder/scripts/example_evaluation.xml 1.2 KB
- skill-library/backend/mcp-builder/scripts/requirements.txt 29 B
- skill-library/backend/mcp-builder/SKILL.md 8.9 KB
- skill-library/backend/observability-design/references/monitoring-patterns.md 10 KB
- skill-library/backend/observability-design/SKILL.md 7.8 KB
- skill-library/backend/pci-compliance/metadata.json 689 B
- skill-library/backend/pci-compliance/SKILL.md 13 KB
- skill-library/backend/performance-profiler/references/profiling-recipes.md 11 KB
- skill-library/backend/performance-profiler/SKILL.md 5.4 KB
- skill-library/backend/runbook-generator/references/runbook-templates.md 1.0 KB
- skill-library/backend/runbook-generator/SKILL.md 1.9 KB
- skill-library/backend/secrets-vault-manager/references/cloud_secret_stores.md 11 KB
- skill-library/backend/secrets-vault-manager/references/emergency_procedures.md 9.7 KB
- skill-library/backend/secrets-vault-manager/references/vault_patterns.md 10 KB
- skill-library/backend/secrets-vault-manager/SKILL.md 16 KB
- skill-library/backend/threat-detection/references/hunt-playbooks.md 6.2 KB
- skill-library/backend/threat-detection/SKILL.md 13 KB
- skill-library/documents/INDEX.md 799 B
- skill-library/documents/markitdown/assets/example_usage.md 10 KB
- skill-library/documents/markitdown/INSTALLATION_GUIDE.md 6.5 KB
- skill-library/documents/markitdown/LICENSE.txt 1.0 KB
- skill-library/documents/markitdown/OPENROUTER_INTEGRATION.md 9.4 KB
- skill-library/documents/markitdown/QUICK_REFERENCE.md 6.7 KB
- skill-library/documents/markitdown/references/api_reference.md 8.8 KB
- skill-library/documents/markitdown/references/file_formats.md 8.8 KB
- skill-library/documents/markitdown/scripts/batch_convert.py 6.5 KB runs code
- skill-library/documents/markitdown/scripts/convert_literature.py 8.7 KB runs code
- skill-library/documents/markitdown/scripts/convert_with_ai.py 7.5 KB runs code
- skill-library/documents/markitdown/SKILL_SUMMARY.md 8.3 KB
- skill-library/documents/markitdown/SKILL.md 11 KB
- skill-library/engineering/context-engineering/SKILL.md 11 KB
- skill-library/engineering/doubt-driven-development/references/orchestration-patterns.md 1.2 KB
- skill-library/engineering/doubt-driven-development/SKILL.md 16 KB
- skill-library/engineering/INDEX.md 2.9 KB
- skill-library/engineering/systematic-debugging/condition-based-waiting-example.ts 4.9 KB runs code
- skill-library/engineering/systematic-debugging/condition-based-waiting.md 3.4 KB
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.
- 1mo ago First seen · 2,039 lines · 57 tokens per session scan B c2c0cacb208d
bx-dev is a skill published in the GitHub repository bish-x/bx-dev-skill (24 stars, last pushed 4mo ago), with no licence file. It adds 57 tokens to every session and 26,270 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 3 findings (subtle steering, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
submit-producti-directories-merged
A workflow for carrying out authorised backlink submissions to product directories and official contact forms, with duplicate checks, verification, evidence, and recovery records. It is intended for execution rather than just researching candidates.
writer
SEO-friendly article writing, audit, and humanization workflow for Markdown content. Use when creating, outlining, editing, auditing, rewriting, or quality-checking blog posts, tutorials, comparisons, listicles, explainers, FAQ sections, excerpts, SEO titles, meta descriptions, tags, or Google-friendly content briefs…
codex-autoresearch
Run repeated, measured Git experiments toward a numeric target; keep improvements and revert failures. Use for autonomous optimization or managing an autoresearch run, not one-shot edits.
backlink-expansion-matrix
Orchestrate an end-to-end backlink expansion project from Semrush or local source files through batch and editorial screening, historical deduplication, workbook delivery, and QA. Use when the request spans more than one backlink stage; do not treat candidates as submitted or published links.
ian-handdrawn-ppt
A workflow for creating finished Chinese hand-drawn technical page images from articles, notes, documents, scripts, or rough ideas.
board-memo
Draft a board or executive summary of an engagement using outcomes, risks and investment decisions. Use when the sponsor needs to brief senior leadership.