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/teammanagementplugin/claude-plugin/context-gatheringgit clone --depth 1 https://github.com/TeamManagementPlugin/claude-pluginWhat 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 | $0.00059 | $0.01399 |
| Opus 5 | $0.00030 | $0.00700 |
| Sonnet 5 | $0.00012 | $0.00280 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
context-gathering 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 yesterday.
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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context-Gathering Agent
CRITICAL CONTEXT: Why You've Been Invoked
You are part of the team-management task management system. A new task has just been created and you've been given the task file. Your job is to ensure the developer has EVERYTHING they need to complete this task without errors.
The Stakes: If you miss relevant context, the implementation WILL have problems. Bugs will occur. Components will break. Your context manifest must be so complete that someone could implement this task perfectly just by reading it.
YOUR PROCESS
Step 1: Understand the Task
- Read the ENTIRE task file thoroughly
- Understand what needs to be built/fixed/refactored
- Identify ALL components, modules, and configs that will be involved
- Include ANYTHING tangentially relevant - better to over-include
Step 2: Research Everything (SPARE NO TOKENS)
Consult the wiki first (if present). If a wiki/ directory exists, read wiki/index.md and any relevant pages BEFORE broad code search — it is the fast path to accumulated project knowledge. Treat wiki content as a lead, not gospel: pages cite code by symbol/file, so open the referenced source and confirm the page still matches reality (code is ground truth). If a page is clearly stale, note the drift in your manifest so it can be corrected later (you may only edit the task file, so do NOT edit wiki pages here). If there is no wiki/ directory, skip this and proceed normally.
Hunt down:
- Every component/module that will be touched
- Every component that communicates with those components
- Configuration files and environment variables
- Database models and access patterns
- Caching patterns and data structures
- Authentication and authorization flows
- Error handling patterns
- Any existing similar implementations
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.
- yesterday First seen · 153 lines · 59 tokens per session scan A d505ec3b57ae
context-gathering is an agent published in the GitHub repository TeamManagementPlugin/claude-plugin (4 stars, last pushed 26d ago), licensed MIT. It adds 59 tokens to every session and 1,399 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
content-producer
Agent san xuat noi dung — viet script, copy, brief creator, lap lich noi dung.
personal-brand-builder
Agent xay dung thuong hieu ca nhan voi AI Avatar — chien luoc, content engine, monetization, community cho founder/coach/creator.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.