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 mishahanin/heading-os --skill competitor-intelgit clone --depth 1 https://github.com/mishahanin/heading-osWrote 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/competitor-intel)<a href="https://agentmods.dev/skills/mishahanin/heading-os/competitor-intel"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/competitor-intel.svg" alt="Measured on agentmods" 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 | $0.00139 | $0.01584 |
| Opus 5 | $0.00069 | $0.00792 |
| Sonnet 5 | $0.00028 | $0.00317 |
| Haiku 4.5 | $0.00014 | $0.00158 |
Grade A, and why
competitor-intel 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Competitor Intelligence
Deep competitive analysis on a specific company or vendor.
Variables
company: [Company name — e.g., "a competing vendor", "a state-aligned vendor", "a state-aligned vendor's DPI division"]
trigger: [Why this analysis now — deal competition, market move, partnership evaluation, investor question]
depth: quick | deep — default: deep
Instructions
Before analyzing, read:
reference/dpi-market-intelligence.md— Existing competitive dataoutputs/deliverables/documents/global-dpi-vendor-landscape-2025.md— Full vendor landscape (check if this company is already profiled)context/strategy.md— 31C's competitive positioningcontext/business-info.md— ODUN.ONE capabilities for comparison
Read reference/search-domains.md for domain filtering configuration.
Search the web for the latest information on this company using two search passes:
Pass 1 -- Industry sources (filtered):
- WebSearch with
allowed_domainsfrom Telecom & DPI + General Tech groups blocked_domains: Blocked Domains list- Query: "[company name] DPI deep packet inspection product launch partnership 2026"
Pass 2 -- Broad company search (blocklist only):
- WebSearch with
blocked_domainsonly (Blocked Domains list) - Query: "[company name] earnings revenue leadership acquisition market moves"
Pass 3 -- Website crawl (for comprehensive product intelligence):
- Use
python scripts/firecrawl.py crawl "[company website]" --limit 10 --include "/product|/pricing|/solution"to get full product and pricing pages.
Evidence Grading & Case File
Before writing the analysis, grade the evidence and maintain the competitor's persistent case file. Full spec: reference/forensic-evidence-grading.md.
- Grade each material claim Confirmed, Deduced, or Hypothesized. Confirmed needs >=2 independent sources or an official filing. Deduced needs a single source or a defensible inference, with the chain shown. Hypothesized is unconfirmed: state what would confirm or refute it. Surface the grade next to the claim, especially in Product Comparison, Their Weaknesses, and Financial health signals. A competitor weakness graded Hypothesized must not be sold as Confirmed.
- Case file at
outputs/intel/cases/[competitor-slug].md(ceo-only). If it exists, read it first and update hypothesis statuses. That is append-only: never delete a refuted theory, flip itsStatustoRefutedwith aResolution. If it does not exist, create it fromreference/templates/intel-case-file.md. This protects the head-to-head from narrative lock-in across quarters.
What ships with it
1 file 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 · 160 lines · 139 tokens per session scan A 27685f3e66f7
competitor-intel is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed yesterday), licensed Apache-2.0. It adds 139 tokens to every session and 1,584 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.