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/0-soft/manus-mcp/agent.updategit clone --depth 1 https://github.com/0-SOFT/Manus-MCPWhat 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 | $0.00000 | $0.00563 |
| Opus 5 | $0.00000 | $0.00282 |
| Sonnet 5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
agent.update 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 --request POST \ What it actually says
agent.update - Manus API
Updates an agent’s nickname and description. Use agent.detail to view current values before updating.
Authorizations
| Parameter | Type | Location | Required |
|---|---|---|---|
x-manus-api-key |
string | header | required |
Body
application/json
| Parameter | Type | Description | Required |
|---|---|---|---|
agent_id |
string | The unique identifier of the agent to update. | required |
nickname |
string | New display name for the agent. | optional |
about |
string | New description or bio for the agent. | optional |
Response
200 OK
application/json
Agent updated successfully.
| Field | Type | Description |
|---|---|---|
ok |
boolean | Whether the request was successful. Example: true |
request_id |
string | Unique identifier for this API request. |
agent |
object | The updated agent object. |
agent.id |
string | Unique identifier for the agent. Use this as agent_id in task.list (with scope=agent_subtask) to view this agent's subtasks. |
agent.task_id |
string | The task ID associated with this agent's creation or configuration. Use task.detail to view the associated task. |
agent.nickname |
string | Display name of the agent. Can be updated via agent.update. |
agent.about |
string | Description or bio of the agent explaining its purpose and specialization. Can be updated via agent.update. |
Code Examples
cURL
curl --request POST \
--url https://api.manus.ai/v2/agent.update \
--header 'Content-Type: application/json' \
--header 'x-manus-api-key: <api-key>' \
--data '
{
"agent_id": "<string>",
"nickname": "<string>",
"about": "<string>"
}
'
200 Response Example
{
"ok": true,
"request_id": "<string>",
"agent": {
"id": "<string>",
"task_id": "<string>",
"nickname": "<string>",
"about": "<string>"
}
}
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 · 70 lines · 0 tokens per session scan A 76cffcae5abf
agent.update is an agent published in the GitHub repository 0-SOFT/Manus-MCP (5 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 563 tokens. 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 2026-08-31.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.