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 saaspegasus/django-boilerplate --skill pegasus-projectsgit clone --depth 1 https://github.com/saaspegasus/django-boilerplateWrote 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/saaspegasus/django-boilerplate/pegasus-projects)<a href="https://agentmods.dev/skills/saaspegasus/django-boilerplate/pegasus-projects"><img src="https://agentmods.dev/badge/skills/saaspegasus/django-boilerplate/pegasus-projects/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/saaspegasus/django-boilerplate/pegasus-projects"><img src="https://agentmods.dev/badge/skills/saaspegasus/django-boilerplate/pegasus-projects.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 5 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium MCP Rug Pull · line 32 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 44 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium MCP Rug Pull · line 45 uvx/uv tool run commands without ==version create a rug-pull risk.Fix: Pin the version: uvx package-name==1.2.3
- medium Excessive Agency · line 231 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00079 | $0.05021 |
| Opus 5 | $0.00039 | $0.02511 |
| Sonnet 5 | $0.00016 | $0.01004 |
| Haiku 4.5 | $0.00008 | $0.00502 |
Grade A, and why
pegasus-projects 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 9d 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 — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Managing SaaS Pegasus projects
You are managing a SaaS Pegasus project on behalf of the user. Pegasus is a Django boilerplate; a "project" is a configuration of features (frontend framework, auth providers, billing, AI, etc.) that the Pegasus build pipeline later renders into a real Django codebase. Your job is to translate the user's intent into the right CLI calls.
Running the CLI
The Pegasus CLI is published on PyPI as pegasus-cli (binary name
pegasus) and also ships installed in every Pegasus project's venv,
pinned to that project's release version.
Pick the invocation form at session start:
- Run
command -v pegasus. - If it returns a path → use bare
pegasus .... This is the preferred form whenever it's available — the local install is version-matched to the project and may even be ahead of what's on PyPI (e.g. unreleased CLI changes that ship with the local repo). - If it returns nothing → use
uvx --from pegasus-cli pegasus ...for every command. The--fromis required because the binary name differs from the package name. Works from any cwd, no venv needed. First call caches the env (a few seconds); subsequent calls are fast.
Don't mix forms within a session. Pick one based on the
command -v result and stay consistent — including for the
auth login command the user runs in a separate terminal (tell them
to use the same form you're using).
For readability, the rest of this document writes commands as bare
pegasus .... Mentally prepend uvx --from pegasus-cli if you're in
the uvx case.
Setup (one time)
Authentication uses an API key from saaspegasus.com.
- Check auth status with
pegasus auth status— non-interactive, safe to run from a Bash tool call. It exits 0 when a key is configured (via~/.pegasus/credentialsor$PEGASUS_API_KEY) and non-zero otherwise. - If unauthenticated, do not try to log in from this session.
pegasus auth loginis interactive (it pauses waiting for the user to paste their key) and will hang if you run it via Bash or the!prefix. Instead, tell the user to open a separate terminal and runpegasus auth loginthemselves. They'll be prompted to paste a key from https://www.saaspegasus.com/. Once that finishes, re-runpegasus auth statushere to confirm and continue. - Alternative for advanced users: export
PEGASUS_API_KEY=<their-key>in the shell that launched Claude Code, then restart this session. - Never try to guess or generate a key yourself — only the user has it.
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.
- 9d ago First seen · 438 lines · 79 tokens per session scan A 8016257ca13b
pegasus-projects is a skill published in the GitHub repository saaspegasus/django-boilerplate (168 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 5,021 once invoked, about $0.0004 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
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.