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 Miosa-osa/OSA --skill opsec-operational-disciplinegit clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/opsec-operational-discipline)<a href="https://agentmods.dev/skills/miosa-osa/osa/opsec-operational-discipline"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/opsec-operational-discipline/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/miosa-osa/osa/opsec-operational-discipline"><img src="https://agentmods.dev/badge/skills/miosa-osa/osa/opsec-operational-discipline.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 | $0.00112 | $0.01224 |
| Opus 5.5 | $0.00045 | $0.00490 |
| Sonnet 5.5 | $0.00022 | $0.00245 |
| Haiku 4.5 | $0.00011 | $0.00122 |
Grade A, and why
opsec-operational-discipline 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 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.
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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OPSEC — Operational Discipline
Derived from T3MP3ST's src/opsec/index.ts (Apache-2.0). OPSEC is a
configuration, not a vibe: pick a level, budget your detections, and act on the
signals.
1. The three OPSEC levels
| Level | max detection events | cooldown after detection | jitter range | traffic blending | log sanitization | cleanup on complete |
|---|---|---|---|---|---|---|
silent |
1 | 300 000 ms (5 min) | 5 000–15 000 ms | yes | yes | yes |
covert (default) |
3 | 60 000 ms (1 min) | 1 000–5 000 ms | yes | yes | yes |
loud |
20 | 2 000 ms | 100–500 ms | no | no | no |
- silent: CTF/lab work or engagements where a single detection ends the mission. One detection event → long cooldown.
- covert: the default for authorized engagements. Small jitter between actions, blending on, three detections before reconsideration.
- loud: only for engagements where the operator has explicitly accepted detection (purple-team exercises, detection-validation runs). No blending, no sanitization, cleanup off — the point is to be seen.
2. Detection events and the abort recommendation
- Every detection (IDS alert, WAF block, honeypot hit, unexpected 403 shift) is
an event with a severity, recorded with an IOC when known
(
ip | domain | hash | signature | behavior). - Crossing the level's
maxDetectionEventsbudget triggers an abort-recommended signal with the reason attached. The recommendation is advisory to the operator but MANDATORY to surface — never swallow it. - After any detection, the cooldown timer starts: no further actions until it expires. Cooldowns are per the level table, not per operator impatience.
3. Pacing mechanics that actually reduce detection
- Jitter: randomize inter-action delay within the level's jitter range — fixed intervals are the single most-detectable pattern in automated tooling.
- Traffic blending: make action traffic resemble legitimate traffic for the target (correct user-agents, realistic header sets, session reuse, business- hours timing where relevant).
- Rate shaping: scan in batches with pauses; prefer passive recon first
(
offensive-osint) and touch the target only when needed. - Log sanitization: strip operator-identifying metadata (hostnames, user
names, internal paths) from anything that leaves your machine. On
silent/covertthis is automatic; onloudit is deliberately off.
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 · 101 lines · 112 tokens per session scan A 4d8fa3c34128
opsec-operational-discipline is a skill published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 11d ago), licensed Apache-2.0. It adds 112 tokens to every session and 1,224 once invoked, about $0.0004 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 2026-09-14.
Other skills, from other repositories
unit-converter
Converts between common units of measurement including temperature, distance, and weight.
code-review
Reviews code changes for quality, security, and best practices.
tui-design
This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with any TUI framework. Activates on mentions of TUI design, terminal UI, Ratatui layout, Ink components, Textual widgets…
bun-development
Fast, modern JavaScript/TypeScript development with the Bun runtime, inspired by oven-sh/bun.
worker-mcp-orchestrator
Guides the coordinator agent on how to orchestrate, delegate to, and supervise local worker agents using the worker-mcp server.
clack
Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.