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 stevesolun/ctx --skill scan-mode-asgit clone --depth 1 https://github.com/stevesolun/ctxWrote 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/stevesolun/ctx/scan-mode-as)<a href="https://agentmods.dev/skills/stevesolun/ctx/scan-mode-as"><img src="https://agentmods.dev/badge/skills/stevesolun/ctx/scan-mode-as/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/stevesolun/ctx/scan-mode-as"><img src="https://agentmods.dev/badge/skills/stevesolun/ctx/scan-mode-as.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 | $0.00038 | $0.00752 |
| Opus 5.5 | $0.00015 | $0.00301 |
| Sonnet 5.5 | $0.00008 | $0.00150 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
scan-mode-as-skill 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 13d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan-Mode-as-Skill
Rather than hard-coding if mode == "quick": do_x() else: do_y() in the agent runtime, treat each operational mode as its own skill that the root agent loads at session start. Each mode skill encodes the phases, priorities, and exit criteria for that mode.
The Three Canonical Modes
Quick — time-boxed rapid assessment
- Prioritize breadth over depth.
- Focus on recent changes (git diffs, modified files) — most likely to contain fresh bugs.
- Load existing wiki notes instead of remapping from scratch.
- Run fast static triage scoped to changed paths.
- One of each essential pass:
semgrep,ast-grep(ortree-sitter), secrets,trivy fs— scoped. - Use case: CI/CD check on a PR.
Standard — balanced systematic assessment
- Full attack surface mapping, but not exhaustive depth on every surface.
- Understand the application before exploiting it.
- Complete authentication/authorization review.
- All major input vectors tested with primary techniques.
- Use case: routine security review, release gate.
Deep — exhaustive assessment
- Maximum coverage, maximum depth. Finding what others miss is the goal.
- Multi-phase: exhaustive recon → business logic deep dive → comprehensive attack surface → vulnerability chaining → persistent testing → comprehensive reporting.
- Agents decompose hierarchically: component → feature → vulnerability, then scale horizontally.
- Use case: thorough audit, adversarial assessment, post-incident deep dive.
Why This Beats Hard-Coding Modes
- Transparent — users can read exactly what "deep" means in markdown, not reverse-engineer control flow.
- Extensible — add
pr_review,red_team,compliance_scanmodes by dropping in new skill files. - Tunable per domain — an org can fork the skill to reflect its own priorities without forking the engine.
- Reusable pattern — the same pattern works for any system that has "modes of operation": deployment modes, migration modes, refactor modes.
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.
- 13d ago First seen · 58 lines · 38 tokens per session scan A 5685fdf68f58
scan-mode-as-skill is a skill published in the GitHub repository stevesolun/ctx (587 stars, last pushed 2d ago), licensed MIT. It adds 38 tokens to every session and 752 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-04.
Other skills, from other repositories
vuln-scanner
Audit trending repos for real security vulnerabilities and disclose responsibly - scan and route findings (PVR / dependency PR), re-submit queued advisories, and send armed email disclosures.
fork-fleet
Fork divergence monitor - tracks where the fleet's active forks diverge in CODE (unique commits, new/modified skills) and CONFIG (enable/var/model/schedule vs upstream), gated on real change.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
autoresearch
Evolve a skill by generating variations, evaluating them, and updating the best version.