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 instructions/punt-labs/postern/claude-mdgit clone --depth 1 https://github.com/punt-labs/posternWrote 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/instructions/punt-labs/postern/claude-md)<a href="https://agentmods.dev/instructions/punt-labs/postern/claude-md"><img src="https://agentmods.dev/badge/instructions/punt-labs/postern/claude-md.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 | $0.03192 | $0.03192 |
| Opus 5 | $0.01596 | $0.01596 |
| Sonnet 5 | $0.00638 | $0.00638 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
postern CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. From any tool (curl, the Pharo IDE, another agent), drive `/repl` to How it starts
The opening of the file, as written. The whole thing — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Postern
Postern is a remote driver for a live Pharo Smalltalk image. It exposes
the running image as an HTTP server: clients send Smalltalk to /repl,
read live documentation from /help, and drive compile / test / inspect
/ commit loops without going through the Pharo GUI. Postern was carved
out of punt-labs/claude-agent-sdk-smalltalk
in early 2026 and ships independently. It has zero Claude dependency
by design — agent integration happens at the HTTP boundary, not in the
Smalltalk image.
This file covers the contributor workflow for developing Postern.
For agents using Postern's runtime (bootstrap, /help flow,
/repl usage, eval token handling), read AGENTS.md.
The public-facing description is in README.md. Architecture and engineering conventions live below.
What Postern Is
A single product, three packages plus a baseline:
Postern-Core— the HTTP eval server.PosternServer(Zinc-backed) binds tolocalhost:8422(or$EVAL_PORT), routes/repl,/health, and/help/*, enforces auth on/replwhen configured, and converts LF line endings to CR before passing source to the Pharo compiler.Postern-Dashboard—PosternDashboardMorphic UI showing live request traffic, status, and request/response bodies. Optional; loaded by thedefaultgroup but never required byPostern-Core.Postern-IcebergExtensions— repairs Iceberg reference-commit drift after CLI git operations. Optional; loaded by thedefaultgroup.BaselineOfPostern— Metacello baseline declaring all three packages plus their*-Testssiblings. Three groups:default(Core + Dashboard + IcebergExtensions),tests,all.
Loading from another image:
Metacello new
baseline: 'Postern';
repository: 'github://punt-labs/postern:main';
load.
Architecture
- HTTP eval server —
PosternServeris Zinc-backed (Pharo's built-in HTTP). Loopback-only by default.startOn:andstartOn:withAuth:bind to localhost;startPublicOn:binds to all interfaces and always requires a token./healthand/helpare unauthenticated;/repluses anX-Eval-Tokenheader read from.tmp/eval-token. - Live
/helpsystem — help content is generated from the loaded image, not static markdown./help/api,/help/browse,/help/pharo,/help/dispatch,/help/lint,/help/git,/help/testing,/help/safety,/help/makefile,/help/lessons. Each section reflects the actual loaded packages; updating the image updates the help. - Eval pipeline —
POST /replbody istext/plainSmalltalk. Server normalises line endings, evaluates inOpalCompiler, returnsprintStringof the result. Errors return the exception's description. No streaming. - Iceberg sync —
Postern-IcebergExtensionsadds arepairAfterClihelper for the case where you've committed via CLI (maketargets,gitdirectly) and Iceberg's reference commit has drifted. - Dashboard — Morphic; opens from World menu or via
PosternDashboard open. Subscribes toPostern-Coreannouncements to render request traffic.
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.
- 5d ago First seen · 279 lines · 3,192 tokens per session scan A 6350faf8c265
postern CLAUDE.md is an instructions file published in the GitHub repository punt-labs/postern (1 stars, last pushed 13d ago), licensed MIT. It adds 3,192 tokens to every session, about $0.0160 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
pharo-agentic-browser AGENTS.md
AGENTS.md instructions for mumez/pharo-agentic-browser, covering agents.md, general rules, implementation rules, project overview and package structure.
apm python.instructions.md
Python development guidelines.
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
pharo-smalltalk-interop-mcp-server CLAUDE.md
Instructions for mumez/pharo-smalltalk-interop-mcp-server, covering claude.md, project overview, development setup, environment variables and common commands.