Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tikalk/adlc-team-skillsnpx agentmods add skills/tikalk/adlc-team-skills/change-publishWrote 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/tikalk/adlc-team-skills/change-publish)<a href="https://agentmods.dev/skills/tikalk/adlc-team-skills/change-publish"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/change-publish/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/tikalk/adlc-team-skills/change-publish"><img src="https://agentmods.dev/badge/skills/tikalk/adlc-team-skills/change-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00073 | $0.02284 |
| Opus 5 | $0.00036 | $0.01142 |
| Sonnet 5 | $0.00015 | $0.00457 |
| Haiku 4.5 | $0.00007 | $0.00228 |
Grade A, and why
change-publish 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 11d 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 — 253 lines — stays where its author put it; the contents beside it link to each section on GitHub.
change-publish
What this skill does
Compile accepted ChDRs into the project's memory layer at {REPO_ROOT}/.adlc/memory/chdr/:
- Validate accepted ChDRs (status + provenance on Decision claims)
- Write each promoted ChDR to
.adlc/memory/chdr/ChDR-{NNN}.mdwith OKF-style frontmatter - Regenerate
{REPO_ROOT}/.adlc/memory/chdr.md— the boot-facing index thatteam-bootinjects into the session-start context (same convention aspdr.md/adr.md) - Mark source drafts
### Status: **Published**
Unlike /levelup-publish (which opens a PR against team-ai-directives), change-publish writes project-local memory — ChDRs describe this repo's evolution and fail the team-wide signal gate. No PR is created; the user commits via their normal flow.
This skill does not run until ChDRs have been accepted via /change-clarify.
When to use
- After
/change-clarify: accepted ChDRs need promotion to memory - After re-running
/change-init: new accepted ChDRs to add to the memory index
When NOT to use
- No accepted ChDRs: run
/change-clarifyfirst - Discovering ChDRs: use
/change-init - Reviewing ChDRs: use
/change-clarify
Process
User Input
$ARGUMENTS
Examples:
"ChDR-001 ChDR-003"— promote only specific ChDRs- Empty input: promote all accepted ChDRs
Role & Context
You are acting as a Memory Publisher — moving accepted ChDRs from local drafts to durable project memory. Your role:
- Validate provenance one more time (the poisoning circuit breaker — a promoted unprovenanced decision poisons every future session via team-boot)
- Write promoted records with frontmatter that
team-bootcan index - Regenerate the
chdr.mdindex so the next session start sees the new decisions
Outline
- Environment Setup (Phase 0): resolve paths, list accepted ChDRs
- Prerequisites Check (Phase 1): ensure accepted ChDRs exist
- Provenance Validation (Phase 2): re-verify every Decision claim has SHA/URL
- Duplicate Check (Phase 3): skip ChDRs already in memory with same issue key
- Memory Record Generation (Phase 4): write
.adlc/memory/chdr/ChDR-{NNN}.md - Index Regeneration (Phase 5): rebuild
.adlc/memory/chdr.md(boot-facing) - Draft Status Update (Phase 6): mark promoted drafts
Published - Summary (Phase 7): report results
What ships with it
2 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.
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.
- 11d ago First seen · 253 lines · 73 tokens per session scan A a1e674d4c628
change-publish is a skill published in the GitHub repository tikalk/adlc-team-skills (133 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 2,284 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
session-management
Context preservation, tiered summarization, resumability.
code-graph
AST-based code graph for fast symbol lookup, dependency analysis, and blast radius via codebase-memory-mcp MCP server.
mnemos
Task-scoped memory lifecycle — typed MnemoGraph prevents lossy context compaction by treating facts/decisions/code-refs/handoffs as distinct node types with per-type eviction policies.
context-shunt
Offload large / multi-file reads to a cheap worker model so raw files never enter Claude's context (token savings).
report
Writes the session final report to a file, then prints only the path and a one-line summary. Fires when the prompt contains "Report per memstack:report", and also when the prompt begins with a standing trigger configured through MEMSTACKREPORTONTASKPROMPTS or MEMSTACKREPORTTRIGGERS. Dormant otherwise.
token-optimization
Use when the user says 'token optimization', 'save tokens', 'context window', 'reduce tokens', 'token stack', or 'TokenStack', or asks about extending context window capacity. Covers TokenStack, the built-in compression proxy that shrinks Claude Code tool output before it reaches the Anthropic API. Do NOT use for…