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 skills/zkysar1/claude-mind/encode-sessionnpx skills add zkysar1/Claude-Mind --skill encode-sessiongit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/encode-session)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/encode-session"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/encode-session.svg" alt="Measured on agentmods" 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 | $0.00120 | $0.14083 |
| Opus 5 | $0.00060 | $0.07042 |
| Sonnet 5 | $0.00024 | $0.02817 |
| Haiku 4.5 | $0.00012 | $0.01408 |
Grade A, and why
encode-session 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 — 996 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/encode-session — Session Learning Consolidation
The chat-context analogue of the autonomous loop's Phase 6.5 (/aspirations-spark)
and Phase 8 (/aspirations-state-update): runs the same structured learning
lanes, but on the just-completed chat session rather than a single goal execution.
Why this exists: in assistant mode the autonomous loop is not running, so the post-goal sparks and state-update lanes never fire. Without a deliberate trigger, chat-mode learning is lost — files get edited, the user moves on, and no encoding happens. /encode-session is that deliberate trigger.
This skill is intentionally a thin orchestrator: it reuses the same scripts
and same protocol blocks as /aspirations-spark Phase 6.5, just adapted for
conversation input rather than goal-record input. The two skills must evolve
together — when one's encoding logic changes, the other should mirror it.
JSON Construction Policy (MANDATORY)
Every encoding sub-lane below invokes an *-add.sh script that accepts JSON
on stdin. Build payloads inline — do NOT materialize them to disk first:
printf '%s' '{"title":"...","type":"success",...}' \
| bash core/scripts/reasoning-bank-add.sh
This applies uniformly to reasoning-bank-add.sh, guardrails-add.sh,
aspirations-add-goal.sh, experience-add.sh, and every other encoding
entry point.
If a payload is too complex to inline (rare — encoding records are
almost always < 2 KB), the only sanctioned scratch home is
agents/<name>/sessions/<SID>/scratch/ (Phase 2.6 — see
.claude/rules/path-resolution.md "L1 Cruft Prevention"). Two prohibitions:
- NEVER
PROJECT_ROOT/.scratch-encode-session/or any other invented top-level dir at the repo root. The L1 hook only governs Write/Edit, so amkdir+ heredoc via Bash bypasses it silently — the prohibition lives at the SKILL.md layer to close that gap. - Always delete scratch at end-of-skill in the same turn that applies the encodings. Orphan staging files are cruft even when the encodings landed successfully.
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 Changed · +2 lines 46bcf12042a0
- 4d ago First seen · 994 lines · 120 tokens per session scan A b1a2e66c81b9
encode-session is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed today), licensed MIT. It adds 120 tokens to every session and 14,083 once invoked, about $0.0006 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 skills, from other repositories
hive.browser-automation
Required before any hive-browser CLI command. The browser is driven from the terminal by running hive-browser ... --json via terminalexec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues…
hive.linkedin-automation
Read before automating LinkedIn with browser tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile…
hive.worker-delegation
Concrete patterns for breaking colony work into parallel worker jobs via runplaybook — when fan-out helps, how to model the goal as a tracker table, write the worker skill, author the playbook, pilot, and let convergence retry/resume the gap.
hive.x-automation
Read before automating X / Twitter with browser tools. Verified flows for post, reply, delete, search-and-engage, plus the Draft.js compose quirks that silently disable the send button. Includes the daily-reply and job-market-reply playbooks. Requires hive.browser-automation for the underlying screenshot + coordinate…
hive.slack-notifications-setup
Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…
hive.writing-hive-skills
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.