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/thepartly/pgroles/agents-mdgit clone --depth 1 https://github.com/thepartly/pgrolesWrote 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/thepartly/pgroles/agents-md)<a href="https://agentmods.dev/instructions/thepartly/pgroles/agents-md"><img src="https://agentmods.dev/badge/instructions/thepartly/pgroles/agents-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 5.1 | $0.02510 | $0.02510 |
| Opus 5 | $0.01255 | $0.01255 |
| Sonnet 5 | $0.00502 | $0.00502 |
| Haiku 4.5 | $0.00251 | $0.00251 |
Grade A, and why
pgroles AGENTS.md 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 today.
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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents when working with code in this repository.
Build & Test Commands
# Build (SQLX_OFFLINE=true needed when no live database is available)
SQLX_OFFLINE=true cargo build --workspace
# Format + lint (always run before committing)
cargo fmt --all
SQLX_OFFLINE=true cargo clippy --all-targets --all-features -- -D warnings
# Unit tests (no database needed)
cargo test --workspace
# Integration tests (requires live PostgreSQL)
export DATABASE_URL=postgres://postgres:testpassword@localhost:5432/pgroles_test
cargo test --workspace -- --include-ignored
# Run a single test
cargo test -p pgroles-core --lib diff::tests::diff_creates_new_roles -- --exact
# CRD drift check (CI compares every committed CRD copy — chart and k8s/ —
# against crdgen output)
scripts/check-crd-drift.sh
scripts/check-crd-docs.sh
# Regenerate CRDs after modifying crd.rs. crdgen writes into the chart; the
# k8s/ copies are duplicates that must be refreshed by hand, and
# check-crd-drift.sh fails if any copy drifts.
cargo run --bin crdgen -- --output-dir charts/pgroles-operator/crds/
cp charts/pgroles-operator/crds/postgrespolicies.pgroles.io.yaml k8s/crd.yaml
cp charts/pgroles-operator/crds/postgrespolicyplans.pgroles.io.yaml k8s/postgrespolicyplan-crd.yaml
cp charts/pgroles-operator/crds/postgrespolicycandidates.pgroles.io.yaml k8s/postgrespolicycandidate-crd.yaml
cp charts/pgroles-operator/crds/ephemeralaccesspolicies.pgroles.io.yaml k8s/ephemeralaccesspolicy-crd.yaml
cp charts/pgroles-operator/crds/ephemeralaccessrequests.pgroles.io.yaml k8s/ephemeralaccessrequest-crd.yaml
Local PostgreSQL for integration tests
docker run --rm --name pgroles-pg16 \
-e POSTGRES_PASSWORD=testpassword \
-e POSTGRES_DB=pgroles_test \
-p 5432:5432 \
postgres:16
Architecture
Data Pipeline
YAML → parse_manifest() → PolicyManifest
→ expand_manifest() → ExpandedManifest (profiles × schemas resolved)
→ RoleGraph::from_expanded() → RoleGraph (desired)
→ [operator only] compose_effective_graph() → RoleGraph (effective desired)
overlays memberships from active EphemeralAccessRequests
DB → inspect() → RoleGraph (current)
→ detect_pg_version() → SqlContext
diff(current, effective desired) → Vec<Change> → sql::render_all_with_context() → SQL
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.
- today Changed · +1 lines · +8 tokens per session 6cbde17cd1ec
- today First seen · 184 lines · 2,502 tokens per session scan A c2d0dac1e5af
pgroles AGENTS.md is an instructions file published in the GitHub repository thepartly/pgroles (19 stars, last pushed today), licensed MIT. It adds 2,510 tokens to every session, about $0.0126 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 2026-09-05.
Other instructions, from other repositories
lms-front AGENTS.md
AGENTS.md instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, development and database (supabase).
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
postgres-skills AGENTS.md
Instructions for neondatabase/postgres-skills, covering agents.md, repository overview, creating a new skill, directory structure and naming conventions.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
pg_exporter AGENTS.md
Instructions for nbari/pg_exporter, covering agents.md, project shape, first steps, devpod workflow (preferred) and local commands.
skillsboard AGENTS.md
AGENTS.md instructions for TommyBez/skillsboard, covering agents.md, cursor cloud specific instructions, what this is, running locally and database schema.