Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add mishahanin/heading-os-marketplace/plugin install heading-opsWrote 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/mishahanin/heading-os-marketplace/deep-think)<a href="https://agentmods.dev/skills/mishahanin/heading-os-marketplace/deep-think"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os-marketplace/deep-think/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/mishahanin/heading-os-marketplace/deep-think"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os-marketplace/deep-think.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 | $0.00178 | $0.02742 |
| Opus 5 | $0.00089 | $0.01371 |
| Sonnet 5 | $0.00036 | $0.00548 |
| Haiku 4.5 | $0.00018 | $0.00274 |
Grade A, and why
deep-think 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 11d 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.
This is a copy
89% identical to deep-think — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Think
Structured sequential reasoning engine. Breaks complex problems into visible, numbered thought steps -- with revision, branching, and maritime-framed recommendations. Every assumption surfaced. Every path explored. Every recommendation backed by the chain of reasoning that produced it.
This skill replaces the Sequential Thinking MCP server. The key improvement: reasoning is visible and challengeable, not hidden inside tool calls.
Variables
problem(required) -- The question, decision, or problem to think throughdepth(optional) --quick(3-5 steps),standard(6-10 steps, default),deep(10-15+ steps)context(optional) -- Additional context, constraints, or files to reference
Customization (optional, Phase 0)
This skill is customization-aware (pilot). Before reasoning, resolve any per-exec overrides: python "${CLAUDE_PLUGIN_ROOT}"/scripts/resolve_customization.py --skill .claude/skills/deep-think. Apply any activation_steps_prepend, persistent_facts (facts to always honour, e.g. a preferred default depth or currency), and output-path overrides from the merged result. On any failure, proceed with the defaults below -- never block. Layout + authoring guide: config/skill-custom/README.md.
When to Engage Proactively
Activate this skill WITHOUT being asked when you detect any of these conditions:
-
Multi-variable decisions -- 3+ competing factors with no obvious weighting. Example: "Should we enter [a new market] through PartnerCo or direct? There's a tender deadline, partner margin question, and a competitive threat."
-
Strategy under uncertainty -- The answer depends on unknowns or contested assumptions. Example: "How should we price the [target-market] deal given competitive pressure from a state-aligned vendor?"
-
Contradictory signals -- Information contains tension or paradox. Example: Pipeline shows strong momentum but CRM health shows RED contacts on key relationships.
-
High-stakes reasoning -- Being wrong is costly: investor positioning, partnership terms, competitive response, market entry timing. Example: "How much technical detail should we share with a potential investor who sits on a competitor's board?"
What ships with it
3 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.
- 11d ago First seen · 263 lines · 178 tokens per session scan A 97f87ccd640a
deep-think is a skill published in the GitHub repository mishahanin/heading-os-marketplace (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 178 tokens to every session and 2,742 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to deep-think, differing in 8 lines, and is treated as a copy.
Other skills, from other repositories
adr
Use when the user knows what they want built and says "/adr", "write an ADR for X", "decide and build X", or "ADR-driven". Turns an intent into a grounded, cited, build-ready ADR at docs/adr/YYYY-MM-DD- .md — load-bearing decisions surfaced to the human — then hands off to nightshift:plan's landing step (the plan is…
domain-modeling
Use when pinning down domain terminology, building a ubiquitous language or project glossary, disambiguating overloaded or vague terms, or maintaining a CONTEXT.md — or when another skill needs to sharpen the domain model. Do NOT use for recording architectural decisions (use adr) or for writing implementation specs.
plan
Use when the user has an idea, feature, or fix that is more than a one-sitting edit and says "plan this", "write a plan for X", "/nightshift:plan", or "what would it take to build X". Sizes the work (trivial → no artifact; medium → a lean plan; large → a short spec first), asks one question at a time until the design…
watch
Use when a Nightwatch spec queue is about to run, or is already running, and someone needs to fire it, watch it, and steer it — "launch nightwatch", "watch the run", "/nightwatch:watch", "pause it", "skip that spec". Runs preflight, launches run.sh, arms the journal and workflow-journal monitors, knows what is safe to…
morning
Use when the user says "/nightshift:morning", "what happened overnight", "how did the night go", "why did the loop stop", or opens a session in a repo with a loop/ directory after a scheduled run. Reads the journal since the last start line and every open land / land:blocked pull request, says per stop what happened…
writing-artifacts
Use when writing or revising a durable written artifact — README, ADR, design doc, PR description, release notes, runbook, error message, user-facing docs. Gives a positive writing system (reader model, sentence positions, document jobs), not a ban-list. Do NOT use for conversational replies to the user (global…