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 blisspixel/primr --skill company-briefgit clone --depth 1 https://github.com/blisspixel/primrWrote 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/blisspixel/primr/company-brief)<a href="https://agentmods.dev/skills/blisspixel/primr/company-brief"><img src="https://agentmods.dev/badge/skills/blisspixel/primr/company-brief/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/blisspixel/primr/company-brief"><img src="https://agentmods.dev/badge/skills/blisspixel/primr/company-brief.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 | $0.00000 | $0.01719 |
| Opus 5 | $0.00000 | $0.00860 |
| Sonnet 5 | $0.00000 | $0.00344 |
| Haiku 4.5 | $0.00000 | $0.00172 |
Grade A, and why
company-brief 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 10d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
company-brief: the primr method, no install required
This skill encodes primr's research methodology so a capable agent host (Claude Code, Cursor, Copilot, or similar) can produce a useful subset of a primr brief using only its built-in tools. It costs the user nothing beyond their existing subscription. Expect a 2,000-5,000 word brief from 15-25 sources, taking roughly 10-25 minutes of agent time.
Be honest with the user about the trade: this is the lite method. The full primr pipeline does 9-tier adaptive scraping across ~50 pages, ATS-targeted hiring-signal extraction, research deepening, cross-validation, trust gates, and QA refinement. If the user wants that depth, point them to pip install primr (needs API keys) and the primr skill.
Ground rules (read first, apply throughout)
- Never fabricate. Every factual claim in the brief comes from something you fetched or a search result you can cite. If you cannot source it, either label it as inference or leave it out.
- Confidence labels on non-obvious claims, using primr's vocabulary exactly:
(Confirmed)- stated by a primary source or by two independent third-party sources(Reported)- stated by one third-party source (news, analyst, review site)(Estimated)- your inference from evidence, e.g. headcount from posting volume; say what it is triangulated from(Hypothesis)- a plausible reading of weak signals, framed as something to validate, never as fact
- Number your citations in the house format. Mark citations inline as
[cite: 1],[cite: 2]; list the full URLs under a## Sourcesheading at the end as[cite: N] Title — URL. A bare inline[1]is not the scored format. - Note absences. What a company does not publish (no pricing page, no leadership page, no engineering blog) is itself a signal; say so rather than padding.
- Thin signal = thin brief. If the company has a four-page website and no postings, deliver a short honest brief plus a list of what could not be determined. Do not inflate.
What ships with it
2 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.
- 10d ago First seen · 91 lines · 0 tokens per session scan A 6bff3f7604f1
company-brief is a skill published in the GitHub repository blisspixel/primr (3 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,719 tokens. 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 2026-08-31.
Other skills, from other repositories
vaaya
Vaaya is the payment system for agents: one MCP server that lets your agent call paid APIs pay-per-call with no API keys. Web search, scraping, image and video generation, code sandboxes, browser automation, email, phone calls, lead enrichment, live data. Priced in cents per call, billed only on success, and every…
autosearch:channel-selection
Group-first channel selection algorithm for v2 tool-supplier architecture. Given a research query + clarify rubrics + channelpriority hints, picks 1-3 relevant groups from the router index, then 3-8 leaf channels from within those groups. Replaces flat-rank selection across 41 channels with a two-stage pick so runtime…
autosearch:citation-index
Deduplicate URLs across all sources, assign stable citation numbers, and merge citations from multiple subagents / sections into one consistent reference list. Prevents "same URL cited as [3] in one paragraph and [17] in another" and "different URLs merged under [5]" bugs that come from per-section synthesis.
autosearch:experience-compact
Promote recurring patterns from experience/patterns.jsonl into the compact experience.md digest (≤120 lines, read by runtime AI before calling the skill). Triggers on N-events / file-size / user-feedback / session-end. Guards against single-success noise and pollution via promotion thresholds.
autosearch:context-retention-policy
Session-level policy for keeping the runtime AI's context window healthy across long research — keep-last-k tool results, offload older evidence to disk, trigger compaction at thresholds. Borrows MiroThinker's keeptoolresult, deepagents' summarization middleware, and deer-flow's SummarizationEvent pattern. Orthogonal…
autosearch:delegate-subtask
Define the execution contract for isolating a research sub-task — input schema, budget, return summary, evidence list, failure status. Complements decompose-task (which only splits the problem) by giving each split a bounded, auditable execution unit the runtime AI can farm out to a sub-agent or parallel session.