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/sgroy10/speclock/claude-mdgit clone --depth 1 https://github.com/sgroy10/speclockWhat 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 | $0.00521 | $0.00521 |
| Opus 5 | $0.00260 | $0.00260 |
| Sonnet 5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
speclock 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://speclock-mcp-production.up.railway.app/health What it actually says
SpecLock Development Rules
MANDATORY RELEASE PROCESS
EVERY code change that touches src/ files MUST follow this exact sequence. NO EXCEPTIONS. Do NOT push without completing ALL steps.
Step 1: Version Bump (ALL 7 files)
package.json
src/mcp/http-server.js → const VERSION = "X.Y.Z"
src/mcp/server.js → const VERSION = "X.Y.Z"
src/core/compliance.js → const VERSION = "X.Y.Z"
src/cli/index.js → SpecLock vX.Y.Z
src/dashboard/index.html → TWO places (header + footer)
Step 2: Commit + Push
git add <files>
git commit -m "vX.Y.Z — description"
git push origin main
Step 3: npm Publish
npm publish
Step 4: Git Tag
git tag vX.Y.Z
git push origin vX.Y.Z
Step 5: Railway Deploy
railway up
Step 6: Verify
curl -s https://speclock-mcp-production.up.railway.app/health
# Must show new version
npm view speclock version
# Must show new version
If you skip ANY step, the release is INCOMPLETE and users will get stale code.
Version File Quick Reference
| File | What to change |
|---|---|
package.json |
"version": "X.Y.Z" |
src/mcp/http-server.js |
const VERSION = "X.Y.Z" |
src/mcp/server.js |
const VERSION = "X.Y.Z" |
src/core/compliance.js |
const VERSION = "X.Y.Z" |
src/cli/index.js |
SpecLock vX.Y.Z in printHelp |
src/dashboard/index.html |
vX.Y.Z in header AND footer |
SpecLock Context
Always call speclock_session_briefing at start of session and speclock_session_summary before ending.
Key Facts
- npm package:
speclock - Railway:
https://speclock-mcp-production.up.railway.app - GitHub:
sgroy10/speclock - Smithery:
sgroy10/speclock - Author: Sandeep Roy
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 · 72 lines · 521 tokens per session scan A db16488a9c95
speclock CLAUDE.md is an instructions file published in the GitHub repository sgroy10/speclock (25 stars, last pushed 15d ago), licensed MIT. It adds 521 tokens to every session, about $0.0026 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 2026-08-30.
Other instructions, from other repositories
memorix CLAUDE.md
Instructions for AVIDS2/memorix, covering memorix - agent instructions for claude code, using memorix memory tools, when to search memory, when to store memory and when to resolve memory.
memorix GEMINI.md
Instructions for AVIDS2/memorix, covering memorix - cross-agent memory rules, session start - bind project, then load context, during session - capture important context, architecture & decisions and bug fixes & problem solving.
server CLAUDE.md
Instructions for aidemd-mcp/server, covering aide — autonomous intent-driven engineering, publishing, fixes go in canonical docs, not memory, local .mcp.json for the aide server and don't run the pipeline on the agent harness.
superskill AGENTS.md
AGENTS.md instructions for permanu/superskill, covering obsidian-mcp — agents.md, project overview, commands, architecture and key patterns.
superpowers-zh CLAUDE.md
Instructions for jnMetaCode/superpowers-zh, covering superpowers — 贡献者指南, 如果你是 ai agent, pull request 要求, 我们不会接受的内容 and 第三方依赖.
spec-kit-zh AGENTS.md
Instructions for loulanyue/spec-kit-zh, covering agents.md, about spec kit and specify, general practices, adding new agent support and current supported agents.