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 primr-zerogit 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/primr-zero)<a href="https://agentmods.dev/skills/blisspixel/primr/primr-zero"><img src="https://agentmods.dev/badge/skills/blisspixel/primr/primr-zero/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/primr-zero"><img src="https://agentmods.dev/badge/skills/blisspixel/primr/primr-zero.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 | $0.00128 | $0.02498 |
| Opus 5.5 | $0.00051 | $0.00999 |
| Sonnet 5.5 | $0.00026 | $0.00500 |
| Haiku 4.5 | $0.00013 | $0.00250 |
Grade A, and why
primr-zero 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 today.
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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Primr Zero
Use Primr for deterministic collection and the current host for expensive reasoning. Primr's collection makes no model API calls. The synthesis is a hard-zero path only when the host is using included plan allowance without billable API-key usage or overages. Host plan limits, network access, electricity, and subscription cost still apply.
Agent-host default
When the current agent receives primr "Company" https://company.example,
"run Primr," or "build a full Primr dossier" without explicit paid intent,
use this skill by default. Keep that clean request as the public interface and
run primr prep only as internal plumbing. Do not ask the user to choose a
Primr mode, and do not infer spend consent from configured provider keys.
Treat paid, metered, provider-backed, premium, explicit dollar-budget, or provider-key requests as paid intent and hand them to the estimate-and-approval workflow. This routing applies to requests addressed to an agent. It does not change the provider-backed behavior of a command that a human runs directly in a terminal.
Before promising zero total incremental spend, verify the billing surface
using information the host makes available. If it is API-key-backed, permits
paid overages, or cannot establish that this run stays within included
allowance, describe Primr model API spend as $0.00 and the host cost as
unknown or potentially metered. Do not silently switch paths. If the user
specifically requires zero total incremental spend, offer a verified
plan-native host session, a checkpointed partial result, or a separately
estimated and approved paid route.
Choose the path
- If a shell and a working Primr launcher are available, run the keyless evidence handoff below.
- If the user supplied a prep bundle, start from its
prep_manifest.jsonandresearch_packet.md. - If the host has no shell, the Primr launcher is unavailable, or installation is declined, use native web research and follow the same report contract. Do not block a useful zero-cost result on installation. State that Primr recon, adaptive scraping, ATS collection, traces, and local artifact QA were unavailable.
- If the host cannot search the web, ask for a prep bundle or source files. Do not produce a supposedly current dossier from model memory.
What ships with it
5 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.
- today Changed · +1 lines fe22a2340656
- 1mo ago Changed · +17 lines 5ee719ecc23d
- 1mo ago First seen · 218 lines · 128 tokens per session scan A d3de33d3581b
primr-zero is a skill published in the GitHub repository blisspixel/primr (3 stars, last pushed today), licensed Apache-2.0. It adds 128 tokens to every session and 2,498 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
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.
autosearch:experience-capture
Append a single skill-execution event to the per-skill experience/patterns.jsonl file. Runs every time a leaf skill is used. Append-only — runtime AI never reads this file directly; only the compacted experience.md digest. Fast tier, no LLM required.