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/stevesolun/ctx/agents-mdgit clone --depth 1 https://github.com/stevesolun/ctxWhat 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 | $0.01695 | $0.01695 |
| Opus 5 | $0.00847 | $0.00847 |
| Sonnet 5 | $0.00339 | $0.00339 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
ctx 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ctx repository notes
The product
CTX Fit finds the cheapest AI coding setup that reliably works on a given repository, and produces the winning configuration as a reviewable change.
The winner is chosen by a lexicographic rule, not a score: filter candidates on a reliability floor, then minimize attributable cost, then tie-break toward simplicity. "Keep your current setup" is a valid and expected answer.
ctx is the human command and ctx fit is the product; older harness commands
live under ctx advanced. ctx-mcp-server is the machine contract name. A few
maintenance console scripts (ctx-init, ctx-scan-repo, ctx-source-registry,
ctx-telemetry-*) still ship — ADR-001's collapse to two entry points is the
destination, not yet the state.
ctx fit # free, local, read-only: profile + readiness
ctx fit --dry-run # what a full evaluation would involve
ctx fit --test --budget 10 # evaluate candidates; spending requires both flags
ctx fit --apply # write the winning configuration
ctx fit --pr # print a PR body and branch name; commits nothing
Where the code lives
src/ctx/cli/fit.py— thectx fitsubcommand: argument surface, human and--jsonrendering, apply/PR handling. Registered fromsrc/ctx/cli/run.py, which is thectxconsole-script entry point (ctx = "ctx.cli.run:main").src/ctx/fit/— the engine, one concern per module:profile.py(normalized repository profile),verification.py(discovering the repository's own test/typecheck/lint/build commands),readiness.py,tasks.py(representative tasks derived from repository history),candidates.pyandrelease_catalog.py(bounded candidate generation),experiment.py(resolve, plan, run),execution.py(trial execution with adaptive reliability stopping),live_runner.pyandproviders.py(driving a real coding agent),recommend.py(choosing a winner, or refusing to),apply.py(recommendation → reviewable repository changes and a PR body).src/tests/fit/— the Fit test suite.
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 · 138 lines · 1,695 tokens per session scan A 299b903b2972
ctx AGENTS.md is an instructions file published in the GitHub repository stevesolun/ctx (581 stars, last pushed 9d ago), licensed MIT. It adds 1,695 tokens to every session, about $0.0085 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
langgraph AGENTS.md
AGENTS.md instructions for langchain-ai/langgraph, covering agents instructions, corridor security analysis, libraries and dependency map.
agentgateway copilot-instructions.md
Copilot instructions for agentgateway/agentgateway: Do not check for, speculate about, or report compilation errors during code review. Compilation diagnostics from review are frequently incorrect; rely on CI to detect and report compilation failures.
hatch3r CLAUDE.md
Instructions for hatch3r/hatch3r, covering hatch3r — development instructions, architecture, development commands, two-axis pillar framework (2.0.0) and orchestrator self-discipline (bypass protection).
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
ken CLAUDE.md
Instructions for townsendmerino/ken, covering claude.md, what this is, repository ownership (read this first), commands and embedding parity & golden fixtures (now in aikit).
gangsta GEMINI.md
Instructions for kucherenko/gangsta, a project described as: AI agentic skills framework for spec-driven development, built on the organizational model of mafia.