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 agentmods add agents/tajd/projektor/rest-endpointsgit clone --depth 1 https://github.com/TAJD/projektorWrote 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/agents/tajd/projektor/rest-endpoints)<a href="https://agentmods.dev/agents/tajd/projektor/rest-endpoints"><img src="https://agentmods.dev/badge/agents/tajd/projektor/rest-endpoints.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 | $0.00020 | $0.01194 |
| Opus 5 | $0.00010 | $0.00597 |
| Sonnet 5 | $0.00004 | $0.00239 |
| Haiku 4.5 | $0.00002 | $0.00119 |
Grade A, and why
rest-endpoints 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Projektor's REST API (/api/*) is the SPA's private, versionless contract — it can
change shape without notice, and agents should use MCP
instead wherever a tool exists. A handful of endpoints are the deliberate exception,
documented here as a stable subset you can depend on. Two kinds qualify:
- No MCP equivalent — things the browser can do that don't fit the JSON-RPC/tool-call shape at all (binary uploads, redirects, public unauthenticated links).
- Fetchable without an MCP session — the shipped specs and playbooks, which have MCP tools too, but which CI jobs and setup scripts need to pull over plain HTTP before any agent is connected.
All /api/* endpoints below require the same bearer-token auth as MCP
(Authorization: Bearer pk_... plus X-Workspace-Slug) unless marked public. The
/auth/* endpoints are the exception — they authenticate the user, not a workspace,
so they take a Cloudflare Access session (or no auth at all) instead.
File attachments
Binary upload/download doesn't fit JSON-RPC, so attachments are REST-only.
| Method | Path | Notes |
|---|---|---|
GET |
/api/files |
List attachments for an issue or wiki page (?entityType=issue|wiki_page&entityId=) |
POST |
/api/files |
Upload a file (multipart) |
POST |
/api/files/links |
Attach an external link instead of a binary |
GET |
/api/files/:id |
Download an attachment |
DELETE |
/api/files/:id |
Delete an attachment |
Auth and tokens
Logging in and minting long-lived tokens are browser flows, not agent tool calls.
| Method | Path | Notes |
|---|---|---|
GET |
/auth/login |
Login redirect (browser only) |
POST |
/auth/tokens |
Mint an API token for the current user |
DELETE |
/auth/tokens/:id |
Revoke a token |
Workspace-scoped API tokens
| Method | Path | Notes |
|---|---|---|
POST |
/api/workspaces/:slug/tokens |
Create a token scoped to a workspace |
GET |
/api/workspaces/:slug/tokens |
List a workspace's tokens |
DELETE |
/api/workspaces/:slug/tokens/:tokenId |
Revoke a workspace token |
GET |
/api/workspaces/:slug/mcp-info |
Ready-to-use MCP connection details for a workspace |
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 · 102 lines · 20 tokens per session scan A 6124f9dd215d
rest-endpoints is an agent published in the GitHub repository TAJD/projektor (39 stars, last pushed 9d ago), licensed MIT. It adds 20 tokens to every session and 1,194 once invoked, about $0.0001 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 agents, from other repositories
retrieval
Two retrieval backends: a lexical index built at compile time that needs no account, and Cloudflare AI Search for hybrid semantic search when you want it.
discovery
How an agent finds these surfaces without being told: the API catalog, DNS-based discovery, an agent-skills index, and the places people actually look.
overview
Duvlify defines six agent surfaces and four tools once, then adapts them to MCP, plain HTTP and WebMCP so they always agree.
mcp
The page outline agents read for line offsets, the in-browser WebMCP bridge and when to run it yourself, the rate limits, and how the surfaces are tested.
builder
Implements a single PLAN.md task in TypeScript (Next.js or Bun). Builds and self-tests; never commits unless told. Dispatched by /build-loop.
reviewer
Read-only code + security gate for a single built task (TypeScript, Next.js or Bun). Returns PASS or FAIL with findings. Dispatched by /build-loop.