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 ericrisco/rsc-harness --skill press-kitgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/press-kit)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/press-kit"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/press-kit.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 | $0.00125 | $0.03028 |
| Opus 5 | $0.00063 | $0.01514 |
| Sonnet 5 | $0.00025 | $0.00606 |
| Haiku 4.5 | $0.00013 | $0.00303 |
Grade A, and why
press-kit 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 3d 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 — 244 lines — stays where its author put it; the contents beside it link to each section on GitHub.
press-kit
You write the document a journalist receives and the kit they pull from — one formatted press release plus the assembled media kit (boilerplate, fact sheet, bios, asset manifest, contact block) laid out so a busy reporter can lift the story without a second email.
The leverage is form, not enthusiasm. 72% of journalists call the press release the single most useful resource a PR team offers, and 79% use releases to generate story ideas (Cision 2025 State of the Media, 3,000+ journalists / 19 markets). The release is not dead — it just gets skipped when it ignores newsroom convention: no dateline, no end marker, a 900-word company history where a 5-W lede should be, no quotable line, no attached asset. Your job is to make the artifact match the form reporters scan, so the story survives the inbox.
You produce: a .md/.txt press release with a header line and ### marker, a
≤100-word boilerplate, a fact sheet, a multimedia manifest with usage notes, exec
bios, a press-contact block, and the short pitch email that carries it. You do
not source the reporter list, write the brand-voice spec, or wire the send.
Is this news, and which type?
First gate: is this news or an ad? A release earns the form only if a reporter
who does not work for you would care. "We updated our pricing page" is not news.
"We raised $12M to do X" is. If the answer is no, route the user to
../marketing/SKILL.md for an owned-channel launch post instead — do not dress an
ad up as a release.
Then pick the type. The type decides what the lede leads with:
| Release type | The lede leads with |
|---|---|
| Product launch | What it does + who it is for + availability date |
| Funding round | Amount + round + lead investor + what it funds |
| Exec hire | Name + role + the credential that makes it news |
| Partnership | The two parties + what the joint offering enables |
| Product update | The capability that is new + the user problem it ends |
| Milestone | The number + why it is a category signal, not a brag |
| Award | The award + the independent body + what it validates |
| Event | What + when/where + why a reporter should attend |
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.
- 3d ago First seen · 244 lines · 125 tokens per session scan A 1d7b35a154bb
press-kit is a skill published in the GitHub repository ericrisco/rsc-harness (65 stars, last pushed yesterday), licensed MIT. It adds 125 tokens to every session and 3,028 once invoked, about $0.0006 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
embargo-management
Produces a complete embargo management brief for a specific embargoed announcement, covering embargo terms, distribution protocol, communication templates, breach response protocol, and a pre-lift checklist.
code-review
Reviews diffs by severity to produce actionable feedback.
pr-workflow
Prepares branches and PRs for clean, reviewable merges.
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…