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 45ck/skill-harness --skill task-memory-profile-plannergit clone --depth 1 https://github.com/45ck/skill-harnessWrote 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/45ck/skill-harness/task-memory-profile-planner)<a href="https://agentmods.dev/skills/45ck/skill-harness/task-memory-profile-planner"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/task-memory-profile-planner/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/45ck/skill-harness/task-memory-profile-planner"><img src="https://agentmods.dev/badge/skills/45ck/skill-harness/task-memory-profile-planner.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 | $0.00036 | $0.00320 |
| Opus 5.5 | $0.00014 | $0.00128 |
| Sonnet 5.5 | $0.00007 | $0.00064 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
task-memory-profile-planner 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 1mo 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.
What it actually says
Task Memory Profile Planner
Use this skill when deciding how a repo should preserve agent task state across sessions, branches, worktrees, and tools.
Process
- Identify who owns task state: human maintainer, agent team, external tracker, or local repo.
- Decide whether the repo needs durable issue graphs, dependency edges, worktree coordination, persistent memories, or only lightweight plan files.
- Compare options:
- Beads for repo-local graph issues and agent session continuity
- lightweight checked-in plan/evidence files
- external tracker such as GitHub Issues, Linear, Jira, or Azure DevOps
- no durable task memory yet
- Define sync, conflict, branch, and closeout rules.
- Record what must never be stored: secrets, raw private tickets, broad mailbox data, private traces, or unredacted customer content.
- Tie the selected memory profile to installer flags and setup proof.
Output
Task-State Owner
Required Memory Shape
Selected Profile
Installer Flags
Sync And Closeout Rules
Privacy Exclusions
Evidence Path
Avoid
- enabling Beads only because it is available
- storing private operational context in generated traces
- mixing task memory with long-term model memory without an explicit policy
- leaving closeout rules separate from the repo's normal quality gates
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.
- 1mo ago First seen · 39 lines · 36 tokens per session scan A 9d611eb239ac
task-memory-profile-planner is a skill published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 320 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
pod-resume
Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.
td-task-management
Task management for AI agents across context windows. Use when agents need to track work, log progress, hand off state, and maintain context across sessions. Includes workflows for single-issue focus, multi-issue work sessions, and structured handoffs. Essential for AI-assisted development where context windows reset…
wisdom-consolidation-log
View CocoWisdom consolidation exceptions. Usage: $wisdom consolidation-log.
register-project
Register an existing project in memory. Use when starting work on a new repo or when a project needs its own context file. Triggers on: 'register project', 'add project to memory', 'track this project', 'create project file'.
do-it-context
Use when project terms, relationships, or invariants drift between user language, docs, and implementation, or when stable project knowledge keeps being rediscovered or the user asks to document it.