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/repoprompt/repoprompt-ce/agents-mdgit clone --depth 1 https://github.com/repoprompt/repoprompt-ceWhat 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 | $0.04478 | $0.04478 |
| Opus 5 | $0.02239 | $0.02239 |
| Sonnet 5 | $0.00896 | $0.00896 |
| Haiku 4.5 | $0.00448 | $0.00448 |
Grade A, and why
repoprompt-ce 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 2d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Notes
This is a Swift Package macOS app for RepoPrompt CE.
Prefer the coordinated developer daemon (make dev-*, see "Developer daemon / coordinated validation" below) for builds, runs, and tests. It runs every job through a lane-serialized queue so concurrent agents do not build, launch, or test over each other, and it returns a ticket for each job so long builds can be detached and checked on later instead of blocking. The plain make / swift / ./Scripts commands shown below are the uncoordinated fallback for when the daemon is unavailable.
Contribution preflight
Before every commit or push, read and run the repository-local $rpce-contribution-check skill:
.agents/skills/rpce-contribution-check/scripts/preflight.sh commit
.agents/skills/rpce-contribution-check/scripts/preflight.sh push
Stage only the intended changes, then use commit mode before creating a commit; rerun it after any staging change, including partial-staging updates. Use push mode after committing but before pushing the intended current branch. These default modes are mandatory safety gates: they enforce redacted staged-index and outgoing-range secret scanning, repository guardrails, and clean push boundaries. Default push does not run heavyweight lint/test/build lanes; use the explicit pr-ready lane when you need the computed-outgoing-range path-selected local PR-ready pass:
.agents/skills/rpce-contribution-check/scripts/preflight.sh pr-ready
Focused validation and release validation remain explicit; use the validation matrix plus commands such as make dev-release-preflight / make dev-release-artifact when the changed boundary requires them. Obtain explicit user approval immediately before any force-push, history rewrite, branch deletion, fork deletion, credential rotation, other GitHub-visible destructive mutation, visible app launch/relaunch, or stopping a visible app.
Local docs/investigations/*.md reports are intentionally left unignored so RepoPrompt tooling can read them. Do not stage or merge these local investigation artifacts unless intentionally requested.
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.
- 2d ago First seen · 306 lines · 4,478 tokens per session scan A 570fbc90d60f
repoprompt-ce AGENTS.md is an instructions file published in the GitHub repository repoprompt/repoprompt-ce (889 stars, last pushed 2d ago), licensed Apache-2.0. It adds 4,478 tokens to every session, about $0.0224 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 instructions, from other repositories
diri AGENTS.md
Instructions for cristicretu/diri, covering diri repository instructions, scope, completed remote architecture baseline, rust workspace map and remote architecture invariants.
awesome-loop-engineering AGENTS.md
Instructions for ChaoYue0307/awesome-loop-engineering, covering repository guidance for ai agents, scope, editing rules, commit identity rule and entry format.
x-harness AGENTS.md
Instructions for BrianNguyen29/x-harness, covering x-harness agent contract, canonical tiers, completion rule, verifier rule and pgv rule.
infinity-context AGENTS.md
Instructions for 777genius/infinity-context, covering agents.md, project intent, source of truth and implementation rule.
ensemblr AGENTS.md
Instructions for ensemblr-hq/ensemblr, covering agent instructions, project naming, app scaffolding requires current official docs, package manager policy and biome policy.
clawdline AGENTS.md
AGENTS.md instructions for sainteye/clawdline, covering working in this repository, shared-tree discipline, root-owned landing closure, root completion receipt and notify before waiting for the user.