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 agents/snowdreamtech/template/speckit.agent-context.updategit clone --depth 1 https://github.com/snowdreamtech/templateWhat 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 | $0.00012 | $0.00315 |
| Opus 5 | $0.00006 | $0.00158 |
| Sonnet 5 | $0.00002 | $0.00063 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
speckit.agent-context.update 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- speckit.agent-context.update — 100% identical, 1 lines differ
- speckit.agent-context.update — 100% identical, 1 lines differ
What it actually says
Update Coding Agent Context
Refresh the managed Spec Kit section inside the active coding agent's context/instruction file (e.g. CLAUDE.md, .github/copilot-instructions.md, AGENTS.md).
Behavior
The script reads the agent-context extension config at
.specify/extensions/agent-context/agent-context-config.yml to discover:
context_file— the path of the coding agent context file to manage.context_markers.start/.end— the delimiters surrounding the managed section. Defaults to<!-- SPECKIT START -->and<!-- SPECKIT END -->when the field is missing.
It then creates, replaces, or appends the managed block so that the section points at the most recent plan path when one can be discovered (specs/<feature>/plan.md).
If context_file is empty or the file cannot be located, the command reports nothing to do and exits successfully.
Execution
- Bash:
.specify/extensions/agent-context/scripts/bash/update-agent-context.sh [plan_path] - PowerShell:
.specify/extensions/agent-context/scripts/powershell/update-agent-context.ps1 [plan_path]
When plan_path is omitted, the script auto-detects the most recently modified specs/*/plan.md.
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 First seen · 30 lines · 12 tokens per session scan A e4b6a0214f62
speckit.agent-context.update is an agent published in the GitHub repository snowdreamtech/template (15 stars, last pushed yesterday), licensed MIT. It adds 12 tokens to every session and 315 once invoked, about $0.0001 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 2026-09-01.
Other agents, from other repositories
content-reviewer
Audit conformite du contenu public. Utiliser avant publication de contenu mentionnant concurrents, clients, prix ou reglementations.
qa-agent
Agent name: QA-Agent Role: QA Lead — full audit OR Orchestrator close-loop verification Human equivalent: QA Lead Classification: Agent (stateful, reasoning, governed) Trust tier at introduction: PROVISIONAL (nsessions < 5) Install: Copy this file to .claude/commands/qa-agent.md in your repo. Invoke with /qa-agent for…
marketing-strategist
Marketing strategy, positioning, copywriting, SEO, CRO, and content creation. Works as a peer to the PM — not a subordinate. Gives the product/market direction while the PM gives the technical direction. Use PROACTIVELY when: working on landing pages, pricing pages, social media posts, email sequences, SEO…
strategic-qa
Tech Lead and QA reviewer for autonomous sprint orchestration. Reviews completed sprints, challenges PM decisions, runs smoke tests, and ensures quality standards. Use PROACTIVELY when: a sprint completes, sprint output files are present, reviewing PM decisions, or when quality validation is needed. Also use when the…
security-auditor
Application security auditor and red team specialist. Use when reviewing auth/authorization, billing/payment, data handling, internet-exposed endpoints, cryptographic operations, or any security-sensitive code.
Claude Code CLAUDE.md Template
프로젝트 루트에 CLAUDE.md를 두면 Claude Code가 매 세션 시작 시 자동 로드한다. Codex의 /.codex/AGENTS.md + 프로젝트 AGENTS.md, Cursor의 .cursor/rules/.mdc와 동등한 역할.