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 deciqAI/knowledge-skills --skill ooda-loopgit clone --depth 1 https://github.com/deciqAI/knowledge-skillsWrote 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/deciqai/knowledge-skills/ooda-loop)<a href="https://agentmods.dev/skills/deciqai/knowledge-skills/ooda-loop"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/ooda-loop/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/deciqai/knowledge-skills/ooda-loop"><img src="https://agentmods.dev/badge/skills/deciqai/knowledge-skills/ooda-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00099 | $0.01950 |
| Opus 5 | $0.00049 | $0.00975 |
| Sonnet 5 | $0.00020 | $0.00390 |
| Haiku 4.5 | $0.00010 | $0.00195 |
Grade A, and why
ooda-loop 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OODA Loop
Overview
Colonel John Boyd (1927-1997) derived the OODA Loop from Korean War air-combat data: the F-86 Sabre achieved a ~10:1 kill ratio over the technically superior MiG-15 because better cockpit visibility and hydraulic controls let pilots cycle Observe → Orient → Decide → Act faster — the slower pilot was always reacting to obsolete information.
The strategic claim: whichever side cycles faster wins — but the bottleneck is almost always Orient (the synthesis step), not raw speed. A team that orients badly just produces wrong decisions faster.
Composes with metacognition (Orient is where reasoning errors surface), feedback-loops (OODA is a competitive feedback loop), first-principles (orient from bedrock, not inherited belief), and momentum-and-form (cycle-time advantage builds momentum).
When to Use
- Competitor outmaneuvers you despite your better resources, capital, or product
- Decisions take longer than the situation allows; losing a competition you should win
- Designing org structure where decision-speed is a competitive variable
- Crisis / incident response — OODA is the operational frame
- AI-native startup out-shipping a slower incumbent as model capabilities shift monthly (AI adoption, AI capex, ship-on-release-day tempo)
Not when: genuinely non-competitive setting; your slowness is high-quality orientation worth keeping; speed was recently pushed at the expense of orient quality.
Coaching Novices (Adaptive Front Door)
- Engine mode: user has a concrete competitive case → run The Process directly.
- Coach mode: user is unfamiliar or has no concrete case → guide step by step.
In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.
- One-line: the side cycling Observe-Orient-Decide-Act faster wins because the slower side reacts to obsolete info — but the bottleneck is usually Orient, not raw speed.
- Check fit: non-competitive settings → not this lens.
- Elicit the real situation: what competition or decision problem are you facing?
[WAIT — do not advance until user responds]
- Run The Process one step at a time: map your loop, estimate the opponent's loop, find the bottleneck, test Orient quality.
[WAIT — do not advance until user responds]
- Close by naming the specific stage to accelerate and, if Orient, the exact mental-model fix they uncovered.
[WAIT — do not advance until user responds]
What ships with it
4 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.
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 · 125 lines · 99 tokens per session scan A 9c5828d3d432
ooda-loop is a skill published in the GitHub repository deciqAI/knowledge-skills (10 stars, last pushed 10d ago), licensed MIT. It adds 99 tokens to every session and 1,950 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
superpowers
Runs 14 numbered engineering protocols in one pack — brainstorm, spec, plan, scaffold, TDD red-green-refactor, systematic debugging, refactoring, code review, performance, security, docs, git hygiene, release checklist, postmortem. Use when the user says "build this feature properly", "debug this systematically"…
objection-handler
Turns prospect pushback into progress — diagnoses the real objection behind the stated one and scripts calm, honest responses for price, timing, competitor, authority and brush-off objections. Use when the user says "they said it's too expensive", "prospect went silent", "they're comparing us to X", "how do I answer…
dspy-debugging-observability
Use for debugging DSPy programs, inspecthistory, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.
bug-reporting
Load this skill whenever you are filing, reviewing, or generating accessibility bug reports — whether from automated tool output, manual testing, user reports, or testing with disabled people. The purpose of this skill is to make accessibility findings easier to report accurately, connect them to real people and…
upstream-first
Load this skill before implementing a fix for a barrier that may originate in a shared component, design system, renderer, or external dependency rather than this project's own code. Decide whether the responsible fix is local, an existing installed capability, or an upstream contribution before writing a workaround.…
debugging
Investigate and safely fix an active, observable software failure, error, regression, or unexpected behavior using reproduction and evidence. Use for the proximate technical cause and remediation. Do not use for a systemic incident postmortem or general performance tuning without a failure.