syntaxai/tdd.md · commit 1e56e71

Homepage: lift compose-statement above the comparison table (#5)

- Move the compose-statement above the table so the "compose, don't
  replace" frame lands before readers parse the table as adversarial.
- Rename the section heading from "What SAMA is not" to "SAMA in your
  agent-coding stack".
- Rename the column header from "Where SAMA differs" to "SAMA's role
  alongside it".

Smallest sub-deliverable of issue #5. Stack-diagram is a follow-up.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

author: syntaxai <[email protected]>
date: 2026-05-22 08:28:18 +01:00
parent: de40911
commit: 1e56e71de377a251697bdf9a3e5a454632e94fe2

1 file changed · +4 −4

modified content/home.md +4 −4

@@ -15,17 +15,17 @@ SAMA is to agent-written code what Conventional Commits is to git history: a sma
15	15
16	16	Read the full discussion in [/sama](/sama). The standalone, language-agnostic [v1.0 specification](https://tdd.md/sama) lives in its own repo so other ecosystems can adopt SAMA without depending on this site.
17	17
18		-## What SAMA is not
	18	+## SAMA in your agent-coding stack
19	19
20		-\| \| What it does \| Where SAMA differs \|
	20	+SAMA composes with the tools you already use. Use AGENTS.md to instruct the agent and SAMA to shape the code; use Factory's scorecard for breadth and SAMA for depth on the architectural pillar; run SWE-bench to grade the agent and SAMA to grade what the agent left behind.
	21	+
	22	+\| \| What it does \| SAMA's role alongside it \|
21	23	\|---\|---\|---\|
22	24	\| [SWE-bench](https://www.swebench.com/) \| Scores agents on real GitHub issues \| SAMA scores codebases, not agents \|
23	25	\| [AGENTS.md](https://agents.md/) \| Tells the agent what to do, in markdown \| SAMA constrains what the code can be \|
24	26	\| [Factory.ai Agent Readiness](https://factory.ai/news/agent-readiness) \| 8-pillar repo maturity scorecard \| SAMA enforces four rules with a binary CI gate \|
25	27	\| [Tweag Agentic Handbook](https://tweag.github.io/agentic-coding-handbook/) \| Describes patterns that work \| SAMA prescribes — and verifies \|
26	28
27		-SAMA composes with all of them. Use AGENTS.md to instruct the agent and SAMA to shape the code; use Factory's scorecard for breadth and SAMA for depth on the architectural pillar; run SWE-bench to grade the agent and SAMA to grade what the agent left behind.
28		-
29	29	## Why this matters
30	30
31	31	LLMs degrade as input context grows. Chroma's [Context Rot research](https://research.trychroma.com/context-rot) shows the effect across all 18 frontier models tested, well within their advertised windows. Aider's [repo-map](https://aider.chat/docs/repomap.html) — structural, not semantic — operates at 4–7% context utilization while semantic indexers spend 14%+ on the same task. Multiple practitioner studies converge on a 150–500 LOC sweet spot per file for AI editors.

raw .diff