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 skills add navendubrajesh/context-management-for-agents --skill kiro-context-architecturegit clone --depth 1 https://github.com/navendubrajesh/context-management-for-agentsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/kiro-context-architecture)<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/kiro-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/kiro-context-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/navendubrajesh/context-management-for-agents/kiro-context-architecture"><img src="https://agentmods.dev/badge/skills/navendubrajesh/context-management-for-agents/kiro-context-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00084 | $0.01013 |
| Opus 5.5 | $0.00034 | $0.00405 |
| Sonnet 5.5 | $0.00017 | $0.00203 |
| Haiku 4.5 | $0.00008 | $0.00101 |
Grade A, and why
kiro-context-architecture 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 2mo 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kiro Context Architecture
Kiro is a spec-driven agentic IDE: persistent context comes from steering files (.kiro/steering/ and ~/.kiro/steering/), foundational docs (product, tech, structure), spec artifacts, and live file references — not from ad-hoc chat history alone. Understanding this stack tells you which levers survive across conversations.
When to Activate
Activate this skill when:
- Diagnosing why Kiro ignores project conventions or uses the wrong stack
- Deciding what belongs in always-on steering vs conditional vs manual inclusion
- Structuring specs (requirements, design, tasks) as durable context for multi-step work
- Choosing workspace vs global steering scope
- Integrating MCP servers and understanding their context cost
Do not activate this skill for adjacent work owned by other skills:
- Do not activate for platform-agnostic attention theory:
context-fundamentals. - Do not activate for writing steering frontmatter and inclusion modes:
kiro-customization. - Do not activate for long-horizon spec session hygiene:
kiro-session-management. - Do not activate for external RAG design:
memory-systems.
Core Concepts
Steering as persistent context
Steering files are markdown documents with optional YAML frontmatter controlling inclusion mode. Workspace steering (.kiro/steering/) overrides global steering (~/.kiro/steering/) on conflict — narrowest applicable scope wins.
Inclusion modes
| Mode | Frontmatter | Loads when |
|---|---|---|
| Always (default) | inclusion: always |
Every interaction |
| File match | inclusion: fileMatch + fileMatchPattern |
Working with matching paths |
| Manual | inclusion: manual |
#filename in chat or / slash command |
| Auto | inclusion: auto + name + description |
Request matches description (skill-like) |
Foundational steering (product.md, tech.md, structure.md) is always included by default — the baseline project understanding.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 78 lines · 84 tokens per session scan A 12ddfe986bf4
kiro-context-architecture is a skill published in the GitHub repository navendubrajesh/context-management-for-agents (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,013 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
kiro-context-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| kiro-context-architecturenavendubrajesh/context-management-for-agents | Skill | 2 | 1mo ago | MIT | A | 84 | Claude Code, Codex |
| knowledge-ingestopenclaw/openclaw | Skill | 394k | yesterday | MIT | A | 80 | Claude Code, Codex |
| mem0-oss-to-platformmem0ai/mem0 | Skill | 68k | 2d ago | Apache-2.0 | A | 217 | Claude Code, Codex |
| forgetasgeirtj/system_prompts_leaks | Skill | 71k | 2d ago | CC0-1.0 | A | 74 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| memoryopensquilla/opensquilla | Skill | 7.1k | 6d ago | Apache-2.0 | A | 44 | Claude Code, Codex |
| ha-data-storesshiwenwen/hope-agent | Skill | 1.9k | yesterday | MIT | A | 115 | Claude Code, Codex |