Borrowing it
Nothing to install: this file belongs to sussdorff/timing-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sussdorff/timing-cli/main/.agents/skills/session-capture/SKILL.mdgit clone --depth 1 https://github.com/sussdorff/timing-cliWrote 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/sussdorff/timing-cli/session-capture)<a href="https://agentmods.dev/skills/sussdorff/timing-cli/session-capture"><img src="https://agentmods.dev/badge/skills/sussdorff/timing-cli/session-capture/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/sussdorff/timing-cli/session-capture"><img src="https://agentmods.dev/badge/skills/sussdorff/timing-cli/session-capture.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 | $0.00046 | $0.00575 |
| Opus 5.5 | $0.00018 | $0.00230 |
| Sonnet 5.5 | $0.00009 | $0.00115 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
session-capture 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 24d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session Capture
Capture durable session knowledge only. This is the lightweight neighbour of
session-retro, not an alternate coding-delivery workflow.
Inputs
- A short summary of the result.
- Material decisions, surprises, and reusable learnings.
- The repository project name when a repository was involved.
- A stable session identifier used as
agent-session:<harness>:<session-id>. The resulting write uses--source-ref=agent-session:<harness>:<session-id>.
Workflow
- Read
workflow/agent-session-captureand extract the summary, decisions, and learnings with its shared semantics. Usescripts/parse_debrief.pyandscripts/aggregate_debriefs.pywhen a structured agent debrief is the available source. - Write the caller-authored capture text to a UTF-8 file. Invoke the helper through
an argv-capable tool with one value per array entry, for example
["uv", "run", "scripts/save_capture.py", "--input-file", "<path>", "--project", "<project>", "--title", "<title>", "--harness", "<harness>", "--session-id", "<session-id>"]. The helper invokesobwith an argv list,--producer=session-capture, and the required stable source reference; it never interpolates capture text into a shell command. - Save a separate decision or learning only when it is independently useful for a
later search. Reuse the same source reference and identify the producing agent with
--producer. - Report the Open Brain reference or the exact reason capture could not run.
Exclusions
- Do not perform Git integration, commits, pushes, or branch operations.
- Do not claim, update, close, or infer work orders.
- Do not stop Docker containers or clean worktrees.
- Do not merge pull requests or run the delivery retro.
Coding delivery ends in the executive-pack merge decision and session-retro.
Tool-argv Shape
["uv", "run", "scripts/save_capture.py", "--input-file", "<caller-authored-capture.txt>",
"--project", "<project>", "--title", "<title>", "--harness", "<harness>",
"--session-id", "<session-id>"]
What ships with it
7 files 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.
- scripts/aggregate_debriefs.py 2.0 KB runs code
- scripts/check-debrief-adherence.py 11 KB runs code
- scripts/parse_debrief.py 5.0 KB runs code
- scripts/save_capture.py 2.7 KB runs code
- scripts/tests/test_check_debrief_adherence.py 11 KB runs code
- scripts/tests/test_parse_debrief.py 8.1 KB runs code
- scripts/tests/test_save_capture.py 1.3 KB runs code
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.
- 24d ago Changed · -3 tokens per session 01855c6e1fc4
- 1mo ago Changed · -2 lines · -1 tokens per session 58c8f43c3db9
- 1mo ago First seen · 62 lines · 50 tokens per session scan A 3832e3696eec
session-capture is a skill published in the GitHub repository sussdorff/timing-cli (1 stars, last pushed 10d ago), licensed MIT. It adds 46 tokens to every session and 575 once invoked, about $0.0002 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 2026-09-24.
Other skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, source notes, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn), including the Learn from conversations and Learn from Memory…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…