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/tool-cataloggit 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/tool-catalog)<a href="https://agentmods.dev/agents/tajd/projektor/tool-catalog"><img src="https://agentmods.dev/badge/agents/tajd/projektor/tool-catalog.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 | $0.00011 | $0.06010 |
| Opus 5 | $0.00005 | $0.03005 |
| Sonnet 5 | $0.00002 | $0.01202 |
| Haiku 4.5 | $0.00001 | $0.00601 |
Grade A, and why
tool-catalog 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Every MCP tool Projektor exposes, grouped by domain, with one-line descriptions.
All inputs and outputs are JSON. The table below is generated from
apps/api/src/mcp/*.ts and freshness-checked by CI, so it always matches the
running server.
116 tools across 22 domains.
Coordination
Agent sessions
| Tool | Description |
|---|---|
register_agent |
Register an agent session, optionally linked to an issue |
heartbeat_agent |
Send a heartbeat to keep an agent session active |
end_agent |
End an agent session |
list_active_agents |
List active agent sessions in the workspace, optionally filtered by issue |
File claims
| Tool | Description |
|---|---|
claim_files |
Claim one or more repo file paths for an issue so the parallel fleet can see what is taken |
release_files |
Release active file claims in the workspace, optionally scoped to an issue |
list_file_claims |
List active file claims in the workspace, optionally filtered by issue or path |
Issue leases
| Tool | Description |
|---|---|
claim_issue |
Atomically lease an issue to an agent session so the parallel fleet doesn't double-work it. Fails if another live session already holds it; reclaims a lease whose session stopped heartbeating. |
release_issue |
Release the active lease on an issue, optionally only if held by a given agent session |
list_issue_leases |
List active issue leases in the workspace, optionally filtered by issue or agent. Each entry's live flag is false when the holder stopped heartbeating (lease is reclaimable). |
Agent messages
| Tool | Description |
|---|---|
post_message |
Post a coordination message to a workspace or issue channel so the agent fleet can communicate |
list_messages |
List coordination messages for a workspace or issue channel, in chronological order |
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 · 247 lines · 11 tokens per session scan A ba51f64da82c
tool-catalog is an agent published in the GitHub repository TAJD/projektor (39 stars, last pushed 9d ago), licensed MIT. It adds 11 tokens to every session and 6,010 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.