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 adbertram/cli-tools --skill deepseek-sessions-cligit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/deepseek-sessions-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/deepseek-sessions-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/deepseek-sessions-cli/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/adbertram/cli-tools/deepseek-sessions-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/deepseek-sessions-cli.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 | $0.00201 | $0.03006 |
| Opus 5.5 | $0.00080 | $0.01202 |
| Sonnet 5.5 | $0.00040 | $0.00601 |
| Haiku 4.5 | $0.00020 | $0.00301 |
Grade A, and why
deepseek-sessions-cli 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.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start>
The deepseek-sessions CLI follows this pattern:
deepseek-sessions <command-group> <action> [arguments] [options]
| Task | Command |
|---|---|
| Get details for one approval request | deepseek-sessions approvals get <APPROVAL_ID> |
| List permission escalation requests and their decisions | deepseek-sessions approvals list |
| Configure authentication credentials | deepseek-sessions auth login |
| Clear stored credentials | deepseek-sessions auth logout |
| Create a new profile from .env.example template | deepseek-sessions auth profiles create <NAME> |
| Delete a profile and its data | deepseek-sessions auth profiles delete <NAME> |
| Get details for a specific profile | deepseek-sessions auth profiles get <NAME> |
| List all profiles and show their auth types and active state | deepseek-sessions auth profiles list |
| Delete a profile and its data | deepseek-sessions auth profiles remove <NAME> |
| Rename a profile, re-keying its secrets to the new profile name | deepseek-sessions auth profiles rename <OLD> <NEW> |
| Activate a profile within its auth type | deepseek-sessions auth profiles select <NAME> |
| Check authentication status across profiles | deepseek-sessions auth status |
| Test authentication by verifying credentials work across profiles | deepseek-sessions auth test |
| Get one conversation, including its user and assistant messages | deepseek-sessions conversations get [CONVERSATION_ID] |
| List conversations within a project's sessions | deepseek-sessions conversations list |
| Get every recorded revision of one goal | deepseek-sessions goals get <GOAL_ID> |
| List standing-goal revisions in a project | deepseek-sessions goals list |
| Get details for a specific project | deepseek-sessions projects get <NAME> |
| List all projects that have dsh sessions | deepseek-sessions projects list |
| Get details for one retry | deepseek-sessions retries get <RETRY_ID> |
| List retryable provider failures in a project | deepseek-sessions retries list |
| Search keywords across every dsh session transcript | deepseek-sessions search run <QUERY> |
| Get full session details including messages, tool calls, and subagents | deepseek-sessions sessions get [SESSION_ID] |
| List sessions | deepseek-sessions sessions list |
| Search for sessions whose transcript contains a query string | deepseek-sessions sessions search <QUERY> |
| Get details for a specific skill load or slash command | deepseek-sessions skills get <SKILL_ID> |
List skill loads (skill tool calls) and slash commands in a project |
deepseek-sessions skills list |
| Get full details for a subagent, including its child session messages | deepseek-sessions subagent-activity get <SUBAGENT_ID> |
| List every subagent session spawned inside a project | deepseek-sessions subagent-activity list |
| Show one session plus every subagent it spawned in a single timeline | deepseek-sessions timeline consolidated |
| Get the timeline for one session | deepseek-sessions timeline get [SESSION_ID] |
| Show a unified timeline across a project's sessions | deepseek-sessions timeline list |
| Get a specific todo by ID | deepseek-sessions todos get <TODO_ID> |
| List the final todo list of each session in a project | deepseek-sessions todos list |
| Get details for a specific tool call | deepseek-sessions tool-calls get <TOOL_CALL_ID> |
| List tool calls in a project | deepseek-sessions tool-calls list |
| Get one turn plus the model round-trips (steps) inside it | deepseek-sessions turns get <TURN> |
| List agent turns with their finish reason, duration, and token cost | deepseek-sessions turns list |
| </quick_start> |
<essential_principles>
MANDATORY: Verify the live command shape before executing ANY deepseek-sessions command.
Consult usage.json when the repo or installed package ships it. If usage.json is absent, use deepseek-sessions --help, the relevant subcommand --help, and README.md instead. Never guess at command syntax.
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.
- today First seen · 195 lines · 201 tokens per session scan A d9d0dfbe562c
deepseek-sessions-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 201 tokens to every session and 3,006 once invoked, about $0.0008 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 2026-11-07.
deepseek-sessions-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| deepseek-sessions-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 201 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| surfnicobailon/surf-cli | Skill | 684 | yesterday | MIT | A | 53 | Claude Code, Codex |
| rdc-cliBANANASJIM/rdc-cli | Skill | 193 | 14d ago | MIT | A | 82 | Claude Code, Codex |
| pixiv-cli-ciFlanChanXwO/pixiv-cli | Skill | 132 | yesterday | MIT | A | 61 | Codex |
| acrawl-mcpMingye-Lu/AgenticCrawler | Skill | 15 | yesterday | MIT | A | 200 | Claude Code, Codex |
| debug-hubrexleimo/aios | Skill | 62 | yesterday | MIT | B | 66 | Claude Code, Codex |