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.
git clone --depth 1 https://github.com/ArtemioPadilla/agent-triforceWrote 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/commands/artemiopadilla/agent-triforce/context-profiles)<a href="https://agentmods.dev/commands/artemiopadilla/agent-triforce/context-profiles"><img src="https://agentmods.dev/badge/commands/artemiopadilla/agent-triforce/context-profiles/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/commands/artemiopadilla/agent-triforce/context-profiles"><img src="https://agentmods.dev/badge/commands/artemiopadilla/agent-triforce/context-profiles.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 | $0.00000 | $0.00277 |
| Opus 5 | $0.00000 | $0.00138 |
| Sonnet 5 | $0.00000 | $0.00055 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
context-profiles 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 9d 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.
What it actually says
View and manage context loading profiles for Agent Triforce skills.
Context profiles control which sections of CLAUDE.md, agent files, and memory are loaded for each skill invocation, reducing token usage for routine tasks.
Steps
- Read
templates/context-profiles.json - Display the profiles in a readable table:
| Skill | Agent | Token Reduction | Memory | Skipped Sections |
|---|---|---|---|---|
| {skill} | {agent} | {estimated_reduction} | {memory_setting} | {skipped sections list} |
-
If the user wants to customize a profile:
- Ask which skill to modify
- Show current sections loaded vs skipped
- Allow adding/removing sections from the skip list
- Save changes to
templates/context-profiles.json
-
Explain that
--full-contextflag on any skill overrides the profile and loads everything
Notes
- Profiles are suggestions — they define what CAN be skipped, not enforcement
implement-featureandrelease-checkalways load full context (0% reduction)checklist-healthhas the highest reduction (45%) since it only needs checklist definitions- Memory settings:
all(full MEMORY.md),last_5_entries(recent only),none(skip memory)
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.
- 9d ago First seen · 28 lines · 0 tokens per session scan A 7587293e8d80
context-profiles is a command published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 277 tokens. 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.
Other commands, from other repositories
rekindle
Recover a fellowship after a session crash. Scans worktrees and quest state, presents a recovery dashboard, and re-spawns Gandalf with recovered quest context. Use when returning to a crashed or expired fellowship session.
ccr
CCR (Compressed Context with Retrieval) — recall the full original of context that greatcto compressed/filtered out, by its short id. The retrieval half of the compression layer.
compress
Compress this workspace's CLAUDE.md by moving mechanically-triggered rules into just-in-time rule packs. Operator-triggered, never automatic.
validate-docs
Validate that site and README documentation is current. Report-only — flags issues without modifying anything.
chronicle
One-time codebase onboarding — interactively extracts your team's conventions, identifies reference files, and generates CLAUDE.md sections so Claude codes the way your team does. Run once per project.
scribe
Create a reusable quest template for a specific type of task (e.g., "API endpoint", "migration"). Encodes project-specific rules and conventions into phase guidance that loads automatically during quests.